<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>5871</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>297</pageFirst>
    <pageLast>304</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2025-04-25</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Scalable engine and the performance of different LLM models in a SLURM based HPC architecture</title>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2025: Tagungsband der 36. Konferenz Halle/Saale, 5.–7. März 2025</parentTitle>
    <identifier type="isbn">978-3-95908-803-9</identifier>
    <identifier type="url">https://www.essv.de/paper.php?id=1265</identifier>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_conferenceName">36. Konferenz Elektronische Sprachsignalverarbeitung (ESSV 2025), Halle/Saale (Germany), 05.-07.03.2025</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Anderson</first_name>
      <last_name>de Lima Luiz</last_name>
    </author>
    <editor>
      <first_name>Sven</first_name>
      <last_name>Grawunder</last_name>
    </editor>
    <author>
      <first_name>Shubham Vijay</first_name>
      <last_name>Kurlekar</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>5870</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>146</pageFirst>
    <pageLast>154</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2025-04-25</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Real-time audio transcriber for language barrier-free classrooms</title>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2025: Tagungsband der 36. Konferenz Halle/Saale, 5.–7. März 2025</parentTitle>
    <identifier type="isbn">978-3-95908-803-9</identifier>
    <identifier type="url">https://www.essv.de/paper.php?id=1247</identifier>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_conferenceName">36. Konferenz Elektronische Sprachsignalverarbeitung (ESSV 2025), Halle/Saale (Germany), 05.-07.03.2025</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Huiyu</first_name>
      <last_name>Liu</last_name>
    </author>
    <editor>
      <first_name>Sven</first_name>
      <last_name>Grawunder</last_name>
    </editor>
    <author>
      <first_name>Gokul</first_name>
      <last_name>Srinivasagan</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>5869</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>93</pageFirst>
    <pageLast>100</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2025-04-25</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Significance-based summarization for lecture recordings: a multi-modal perspective</title>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2025: Tagungsband der 36. Konferenz Halle/Saale, 5.–7. März 2025</parentTitle>
    <identifier type="url">https://www.essv.de/paper.php?id=1240</identifier>
    <identifier type="isbn">978-3-95908-803-9</identifier>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_conferenceName">36. Konferenz Elektronische Sprachsignalverarbeitung (ESSV 2025), Halle/Saale (Germany), 05.-07.03.2025</enrichment>
    <author>
      <first_name>Raviteja</first_name>
      <last_name>Boddu</last_name>
    </author>
    <editor>
      <first_name>Sven</first_name>
      <last_name>Grawunder</last_name>
    </editor>
    <author>
      <first_name>Anderson</first_name>
      <last_name>de Lima Luiz</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>5822</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace>Piscataway</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2025-04-11</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Evaluating Snippet Significance: A Framework for Audio and Text-Based Dialogue Summarization</title>
    <parentTitle language="eng">ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, Conference Proceedings</parentTitle>
    <identifier type="isbn">979-8-3503-6874-1</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="local_crossrefDocumentType">proceedings-article</enrichment>
    <enrichment key="local_crossrefLicence">https://doi.org/10.15223/policy-029</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,Enrichmentconference_title,Enrichmentconference_place,PublisherName,TitleMain_1,TitleParent_1,PageNumber,PageFirst,PageLast,CompletedYear,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="conference_title">ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</enrichment>
    <enrichment key="conference_place">Hyderabad, India</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1109/ICASSP49660.2025.10888790</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_conferenceName">2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025), Hyderabad (India), 06.-11.04.2025</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Anderson</first_name>
      <last_name>de Lima Luiz</last_name>
    </author>
    <author>
      <first_name>Raviteja</first_name>
      <last_name>Boddu</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>1537</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>3236</pageFirst>
    <pageLast>3240</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace>Grenoble</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-02-27</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Compact Speaker Embedding: lrx-vector</title>
    <parentTitle language="eng">Proceedings Interspeech 2020</parentTitle>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.21437/Interspeech.2020-2106</enrichment>
    <enrichment key="THI_conferenceName">Interspeech 2020, online, 25.-29.10.2020</enrichment>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <author>
      <first_name>Jonathan</first_name>
      <last_name>Huang</last_name>
    </author>
    <author>
      <first_name>Tobias</first_name>
      <last_name>Bocklet</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speaker recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>x-vector</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>low power</value>
    </subject>
    <collection role="persons" number="40770">Georges, Munir</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
  </doc>
  <doc>
    <id>2617</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>2</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>ACM</publisherName>
    <publisherPlace>New York</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2022-08-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">DNN Optimization in Low-Power Speech Processing</title>
    <parentTitle language="eng">CSCS '20: ACM Computer Science in Cars Symposium - Extended Abstracts</parentTitle>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_conferenceName">4th ACM Computer Science in Cars Symposium (CSCS 2020), online, 18.10.2020</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
  </doc>
  <doc>
    <id>3054</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>187</pageFirst>
    <pageLast>192</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>Association for Computational Linguistics</publisherName>
    <publisherPlace>Stroudsburg</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2023-01-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Hierarchical Multi-Task Transformers for Crosslingual Low Resource Phoneme Recognition</title>
    <abstract language="eng">This paper proposes a method for multilingual phoneme recognition in unseen, low resource languages. We propose a novel hierarchical multi-task classifier built on a hybrid convolution-transformer acoustic architecture where articulatory attribute and phoneme classifiers are optimized jointly.&#13;
The model was evaluated on a subset of 24 languages from the Mozilla Common Voice corpus. We found that when using regular multi-task learning, negative transfer effects occurred between attribute and phoneme classifiers. They were reduced by the hierarchical architecture. When evaluating zero-shot crosslingual transfer on a data set with 95 languages, our hierarchical multi-task classifier achieves an absolute PER improvement of 2.78% compared to a phoneme-only baseline.</abstract>
    <parentTitle language="eng">Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022)</parentTitle>
    <identifier type="url">https://aclanthology.org/2022.icnlsp-1.21</identifier>
    <identifier type="urn">urn:nbn:de:bvb:573-30544</identifier>
    <identifier type="isbn">978-1-959429-36-4</identifier>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">ja</enrichment>
    <enrichment key="THI_conferenceName">5th International Conference on Natural Language and Speech Processing (ICNLSP 2022), Trento (Italy), 16.-17.12.2022</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Creative Commons BY 4.0</licence>
    <author>
      <first_name>Kevin</first_name>
      <last_name>Glocker</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speech recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>multilingual</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>zero-shot</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>multi-task learning</value>
    </subject>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-haw/files/3054/2022.icnlsp-1.21.pdf</file>
  </doc>
  <doc>
    <id>3782</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace>Piscataway</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">An End-to-End Neural Network for Image-to-Audio Transformation</title>
    <parentTitle language="eng">Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</parentTitle>
    <identifier type="isbn">978-1-7281-6327-7</identifier>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_conferenceName">ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island (Greece), 04.-10.06.2023</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1109/ICASSP49357.2023.10096121</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Liu</first_name>
      <last_name>Chen</last_name>
    </author>
    <author>
      <first_name>Michael</first_name>
      <last_name>Deisher</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>OCR</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>TTS</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>image-to-speech</value>
    </subject>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>1623</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>257</pageFirst>
    <pageLast>261</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>ACL</publisherName>
    <publisherPlace>Stroudsburg</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2022-03-01</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Audio-Visual Recipe Guidance for Smart Kitchen Devices</title>
    <parentTitle language="eng">ICNLSP 2021: Proceedings of the 4th International Conference on Natural Language and Speech Processing</parentTitle>
    <identifier type="isbn">978-1-955917-18-6</identifier>
    <enrichment key="THI_review">editorial review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_conferenceName">ICNLSP 2021: 4th International Conference on Natural Language and Speech Processing, online, 12.-13. November 2021</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_relatedIdentifier">https://aclanthology.org/2021.icnlsp-1.30</enrichment>
    <enrichment key="THI_DownloadUrl">https://paperswithcode.com/paper/audio-visual-recipe-guidance-for-smart</enrichment>
    <author>
      <first_name>Caroline</first_name>
      <last_name>Kendrick</last_name>
    </author>
    <author>
      <first_name>Mariano</first_name>
      <last_name>Frohnmaier</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>1624</id>
    <completedYear/>
    <publishedYear>2019</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>809</pageFirst>
    <pageLast>813</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace>Grenoble</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-03-01</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Ultra-Compact NLU: Neuronal Network Binarization as Regularization</title>
    <parentTitle language="eng">Proceedings Interspeech 2019</parentTitle>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.21437/Interspeech.2019-2591</enrichment>
    <enrichment key="THI_conferenceName">Interspeech 2019, Graz (Austria), 15.-19.09.2019</enrichment>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <author>
      <first_name>Krzysztof</first_name>
      <last_name>Czarnowski</last_name>
    </author>
    <author>
      <first_name>Tobias</first_name>
      <last_name>Bocklet</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>ASR</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>NLU</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>SLU</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>binary DNN</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>regularization</value>
    </subject>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>1625</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2036</pageFirst>
    <pageLast>2037</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace>Grenoble</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-03-01</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Speech Recognition and Understanding on Hardware-Accelerated DSP</title>
    <parentTitle language="eng">Interspeech 2017: Situated interaction</parentTitle>
    <identifier type="url">https://www.isca-speech.org/archive/interspeech_2017/stemmer17_interspeech.html</identifier>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_conferenceName">Interspeech 2017, Stockholm (Sweden), 20.-24.08.2017</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.21437/Interspeech.2017</enrichment>
    <author>
      <first_name>Georg</first_name>
      <last_name>Stemmer</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <author>
      <first_name>Joachim</first_name>
      <last_name>Hofer</last_name>
    </author>
    <author>
      <first_name>Piotr</first_name>
      <last_name>Rozen</last_name>
    </author>
    <author>
      <first_name>Josef</first_name>
      <last_name>Bauer</last_name>
    </author>
    <author>
      <first_name>Jakub</first_name>
      <last_name>Nowicki</last_name>
    </author>
    <author>
      <first_name>Tobias</first_name>
      <last_name>Bocklet</last_name>
    </author>
    <author>
      <first_name>Hannah R.</first_name>
      <last_name>Colett</last_name>
    </author>
    <author>
      <first_name>Ohad</first_name>
      <last_name>Falik</last_name>
    </author>
    <author>
      <first_name>Michael</first_name>
      <last_name>Deisher</last_name>
    </author>
    <author>
      <first_name>Sylvia J.</first_name>
      <last_name>Downing</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speech recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>natural language understanding</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>neural network hardware</value>
    </subject>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>1626</id>
    <completedYear/>
    <publishedYear>2014</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>3271</pageFirst>
    <pageLast>3275</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace>Piscataway</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-03-01</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Accurate client-server based speech recognition keeping personal data on the client</title>
    <parentTitle language="eng">2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)</parentTitle>
    <identifier type="isbn">978-1-4799-2893-4</identifier>
    <identifier type="issn">2379-190X</identifier>
    <identifier type="issn">1520-6149</identifier>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1109/ICASSP.2014.6854205</enrichment>
    <enrichment key="THI_conferenceName">2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence (Italy), 04.-09.05.2014</enrichment>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <author>
      <first_name>Stephan</first_name>
      <last_name>Kanthak</last_name>
    </author>
    <author>
      <first_name>Dietrich</first_name>
      <last_name>Klakow</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Dynamic Language Model</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Acoustic Filler</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Data Privacy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Client-Server Speech Recognition</value>
    </subject>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>1627</id>
    <completedYear/>
    <publishedYear>2013</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>642</pageFirst>
    <pageLast>646</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace>Grenoble</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-03-01</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Transducer-based speech recognition with dynamic language models</title>
    <parentTitle language="eng">Proceedings Interspeech 2013</parentTitle>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_conferenceName">Interspeech 2013, Lyon (France), 25.-29.08.2013</enrichment>
    <enrichment key="THI_relatedIdentifier">doi.org/10.21437/Interspeech.2013-185</enrichment>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <author>
      <first_name>Stephan</first_name>
      <last_name>Kanthak</last_name>
    </author>
    <author>
      <first_name>Dietrich</first_name>
      <last_name>Klakow</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>embedded speech recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>embedded grammars</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Markov language models</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>transducer nesting</value>
    </subject>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>3923</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2258</pageFirst>
    <pageLast>2262</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace>Grenoble</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes</title>
    <parentTitle language="eng">INTERSPEECH 2023</parentTitle>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T04:24:36Z","timestamp":1692073476679},"publisher-location":"ISCA","reference-count":0,"publisher":"ISCA","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.21437\/interspeech.2023-772","type":"proceedings-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T08:22:20Z","timestamp":1692001340000},"source":"Crossref","is-referenced-by-count":0,"title":["Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes"],"prefix":"10.21437","author":[{"given":"Kevin","family":"Glocker","sequence":"first","affiliation":[]},{"given":"Aaricia","family":"Herygers","sequence":"additional","affiliation":[]},{"given":"Munir","family":"Georges","sequence":"additional","affiliation":[]}],"member":"8866","published-online":{"date-parts":[[2023,8,20]]},"event":{"name":"INTERSPEECH 2023","acronym":"interspeech_2023"},"container-title":["INTERSPEECH 2023"],"original-title":[],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T08:27:19Z","timestamp":1692001639000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.isca-speech.org\/archive\/interspeech_2023\/glocker23_interspeech.html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,20]]},"references-count":0,"URL":"http:\/\/dx.doi.org\/10.21437\/interspeech.2023-772","relation":{},"published":{"date-parts":[[2023,8,20]]}}}</enrichment>
    <enrichment key="local_crossrefDocumentType">proceedings-article</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,Enrichmentconference_title,PublisherName,PublisherPlace,TitleMain_1,TitleParent_1,CompletedYear</enrichment>
    <enrichment key="conference_title">INTERSPEECH 2023</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_conferenceName">INTERSPEECH 2023, Dublin (Ireland), 20.-24.08.2023</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.21437/Interspeech.2023-772</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_furtherversion">https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/3730</enrichment>
    <author>
      <first_name>Kevin</first_name>
      <last_name>Glocker</last_name>
    </author>
    <author>
      <first_name>Aaricia</first_name>
      <last_name>Herygers</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speech recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>cross-lingual</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>zero-shot</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>phoneme recognition</value>
    </subject>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>3993</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>141</pageFirst>
    <pageLast>145</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>International Speech Communication Association (ISCA)</publisherName>
    <publisherPlace>Baixas</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2023-09-25</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Unsupervised Multilingual Topic Segmentation of Video Lectures: What can Hierarchical Labels tell us about the Performance?</title>
    <parentTitle language="eng">Proceedings 9th Workshop on Speech and Language Technology in Education (SLaTE)</parentTitle>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.21437/SLaTE.2023-27</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_conferenceName">9th Workshop on Speech and Language Technology in Education (SLaTE 2023), Dublin (Ireland), 18.08.-20.08.2023</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <author>
      <first_name>Steffen</first_name>
      <last_name>Freisinger</last_name>
    </author>
    <author>
      <first_name>Fabian</first_name>
      <last_name>Schneider</last_name>
    </author>
    <author>
      <first_name>Aaricia</first_name>
      <last_name>Herygers</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <author>
      <first_name>Tobias</first_name>
      <last_name>Bocklet</last_name>
    </author>
    <author>
      <first_name>Korbinian</first_name>
      <last_name>Riedhammer</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>topic segmentation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>video lectures</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>hierarchical topics</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>multilingual</value>
    </subject>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>5119</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-09-19</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">A Pipeline for Automatic Construction and Applications of College Curriculum Knowledge Graph</title>
    <parentTitle language="eng">TSD 2024 Paper Abstracts</parentTitle>
    <identifier type="url">https://www.tsdconference.org/tsd2024/abstracts.html#I1270</identifier>
    <enrichment key="THI_review">nein</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_conferenceName">27th International Conference on Text, Speech and Dialogue, Brno (Czech Republic), 09.-13.09.2024</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <author>
      <first_name>Di</first_name>
      <last_name>Wu</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>5055</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>214</pageFirst>
    <pageLast>226</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Cham</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2024-09-02</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Evaluation Metrics in LLM Code Generation</title>
    <parentTitle language="eng">Text, Speech, and Dialogue: 27th International Conference, TSD 2024 Brno, Czech Republic, September 9–13, 2024 Proceedings, Part I</parentTitle>
    <identifier type="isbn">978-3-031-70563-2</identifier>
    <identifier type="isbn">978-3-031-70562-5</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:21:45Z","timestamp":1725150105776},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705625","type":"print"},{"value":"9783031705632","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70563-2_17","type":"book-chapter","created":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:29:51Z","timestamp":1725143391000},"page":"214-226","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation Metrics in\u00a0LLM Code Generation"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0009-0002-6290-9757","authenticated-orcid":false,"given":"Kai","family":"Hartung","sequence":"first","affiliation":[]},{"given":"Sambit","family":"Mallick","sequence":"additional","affiliation":[]},{"given":"S\u00f6ren","family":"Gr\u00f6ttrup","sequence":"additional","affiliation":[]},{"given":"Munir","family":"Georges","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,1]]},"reference":[{"key":"17_CR1","unstructured":"Code metrics values. https:\/\/learn.microsoft.com\/en-us\/visualstudio\/code-quality\/code-metrics-values?view=vs-2022. Accessed 13 Feb 2023"},{"key":"17_CR2","doi-asserted-by":"publisher","unstructured":"Abu-Aisheh, Z., Raveaux, R., Ramel, J.Y., Martineau, P.: An exact graph edit distance algorithm for solving pattern recognition problems. In: 4th International Conference on Pattern Recognition Applications and Methods 2015, Lisbon, Portugal (2015). https:\/\/doi.org\/10.5220\/0005209202710278. https:\/\/hal.science\/hal-01168816","DOI":"10.5220\/0005209202710278"},{"key":"17_CR3","unstructured":"Austin, J., et\u00a0al.: Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Bafatakis, N., et al.: Python coding style compliance on stack overflow. In: 2019 IEEE\/ACM 16th International Conference on Mining Software Repositories (MSR), pp. 210\u2013214. IEEE (2019)","DOI":"10.1109\/MSR.2019.00042"},{"issue":"4","key":"17_CR5","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1109\/TSE.2009.70","volume":"36","author":"RP Buse","year":"2009","unstructured":"Buse, R.P., Weimer, W.R.: Learning a metric for code readability. IEEE Trans. Softw. Eng. 36(4), 546\u2013558 (2009)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"17_CR6","unstructured":"Chen, M., et\u00a0al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"issue":"6","key":"17_CR7","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/s10664-022-10193-8","volume":"27","author":"S Chowdhury","year":"2022","unstructured":"Chowdhury, S., Holmes, R., Zaidman, A., Kazman, R.: Revisiting the debate: are code metrics useful for measuring maintenance effort? Empir. Softw. Eng. 27(6), 158 (2022)","journal-title":"Empir. Softw. Eng."},{"issue":"8","key":"17_CR8","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/2.303623","volume":"27","author":"D Coleman","year":"1994","unstructured":"Coleman, D., Ash, D., Lowther, B., Oman, P.: Using metrics to evaluate software system maintainability. Computer 27(8), 44\u201349 (1994)","journal-title":"Computer"},{"key":"17_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2023.111741","volume":"203","author":"M Evtikhiev","year":"2023","unstructured":"Evtikhiev, M., Bogomolov, E., Sokolov, Y., Bryksin, T.: Out of the BLEU: how should we assess quality of the Code Generation models? J. Syst. Softw. 203, 111741 (2023)","journal-title":"J. Syst. Softw."},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Feng, Z., et\u00a0al.: Codebert: a pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"17_CR11","unstructured":"Guido van Rossum, Barry Warsaw, Alyssa Coghlan: PEP 8 - Style Guide for Python Code (2001). https:\/\/peps.python.org\/pep-0008\/"},{"key":"17_CR12","unstructured":"Gunasekar, S., et al.: Textbooks Are All You Need (2023). https:\/\/arxiv.org\/pdf\/2306.11644v2.pdf. _eprint: 2306.11644"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Hagberg, A.A., Schult, D.A., Swart, P.J.: Exploring network structure, dynamics, and function using networkX. In: Varoquaux, G., Vaught, T., Millman, J. (eds.) Proceedings of the 7th Python in Science Conference, Pasadena, CA, USA, pp. 11 \u2013 15 (2008)","DOI":"10.25080\/TCWV9851"},{"key":"17_CR14","unstructured":"Halstead, M.H.: Elements of Software Science (Operating and programming systems series). Elsevier Science Inc. (1977)"},{"key":"17_CR15","doi-asserted-by":"publisher","unstructured":"Heitlager, I., Kuipers, T., Visser, J.: A practical model for measuring maintainability. In: 6th International Conference on the Quality of Information and Communications Technology (QUATIC 2007), pp. 30\u201339 (2007). https:\/\/doi.org\/10.1109\/QUATIC.2007.8. https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=4335232","DOI":"10.1109\/QUATIC.2007.8"},{"key":"17_CR16","unstructured":"Li, Y., Bubeck, S., Eldan, R., Giorno, A.D., Gunasekar, S., Lee, Y.T.: Textbooks are all you need ii: phi-1.5 technical report (2023)"},{"issue":"6624","key":"17_CR17","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1126\/science.abq1158","volume":"378","author":"Y Li","year":"2022","unstructured":"Li, Y., et al.: Competition-level code generation with alphacode. Science 378(6624), 1092\u20131097 (2022)","journal-title":"Science"},{"key":"17_CR18","unstructured":"Liu, J., Xia, C.S., Wang, Y., ZHANG, L.: Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation. In: Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 21558\u201321572. Curran Associates, Inc. (2023)"},{"key":"17_CR19","doi-asserted-by":"publisher","unstructured":"McCabe, T.: A complexity measure. IEEE Trans. Softw. Eng. SE-2(4), 308\u2013320 (1976). https:\/\/doi.org\/10.1109\/TSE.1976.233837. https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=1702388","DOI":"10.1109\/TSE.1976.233837"},{"key":"17_CR20","unstructured":"Lacchia, M.: Introduction to Code Metrics (2020). https:\/\/radon.readthedocs.io\/en\/latest\/intro.html"},{"key":"17_CR21","unstructured":"Nijkamp, E., et al.: Codegen: an open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:2203.13474 (2022)"},{"key":"17_CR22","unstructured":"Achiam, J., et\u00a0al.: OpenAI: Gpt-4 technical report (2023)"},{"key":"17_CR23","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics, Philadelphia (2002). https:\/\/doi.org\/10.3115\/1073083.1073135. https:\/\/aclanthology.org\/P02-1040","DOI":"10.3115\/1073083.1073135"},{"key":"17_CR24","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks (2019). https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"17_CR26","unstructured":"Ren, S., et al.: CodeBLEU: a method for automatic evaluation of code synthesis (2020). https:\/\/arxiv.org\/pdf\/2009.10297.pdf. _eprint: 2009.10297"},{"key":"17_CR27","unstructured":"Rozi\u00e8re, B., et al.: Code Llama: open foundation models for code (2023). https:\/\/arxiv.org\/pdf\/2308.12950.pdf. _eprint: 2308.12950"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, W., Joty, S., Hoi, S.C.: Codet5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"17_CR29","unstructured":"Wei, Y., Wang, Z., Liu, J., Ding, Y., Zhang, L.: Magicoder: source code is all you need (2023)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70563-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:35:02Z","timestamp":1725143702000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70563-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705625","9783031705632"],"references-count":29,"URL":"http:\/\/dx.doi.org\/10.1007\/978-3-031-70563-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}</enrichment>
    <enrichment key="local_crossrefDocumentType">book-chapter</enrichment>
    <enrichment key="local_crossrefLicence">https://www.springernature.com/gp/researchers/text-and-data-mining</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorIdentifierOrcid_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PublisherName,PublisherPlace,TitleMain_1,Language,TitleParent_1,PageNumber,PageFirst,PageLast,CompletedYear,IdentifierIsbn,IdentifierIssn,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1007/978-3-031-70563-2_17</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_conferenceName">27th International Conference on Text, Speech and Dialogue (TSD 2024), Brno (Czech Republic), 09.-13.09.2024</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Kai</first_name>
      <last_name>Hartung</last_name>
    </author>
    <editor>
      <first_name>Elmar</first_name>
      <last_name>Nöth</last_name>
    </editor>
    <author>
      <first_name>Sambit</first_name>
      <last_name>Mallick</last_name>
    </author>
    <editor>
      <first_name>Aleš</first_name>
      <last_name>Horák</last_name>
    </editor>
    <author>
      <first_name>Sören</first_name>
      <last_name>Gröttrup</last_name>
    </author>
    <editor>
      <first_name>Petr</first_name>
      <last_name>Sojka</last_name>
    </editor>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <collection role="institutes" number="15986">THI Business School</collection>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
    <collection role="persons" number="40771">Gröttrup, Sören</collection>
  </doc>
  <doc>
    <id>5057</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>275</pageFirst>
    <pageLast>287</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Cham</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2024-09-02</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Joint-Average Mean and Variance Feature Matching (JAMVFM) Semi-supervised GAN with Additional-Objective Training Function for Intent Detection</title>
    <parentTitle language="eng">Text, Speech, and Dialogue: 27th International Conference, TSD 2024 Brno, Czech Republic, September 9–13, 2024 Proceedings, Part II</parentTitle>
    <identifier type="isbn">978-3-031-70566-3</identifier>
    <identifier type="isbn">978-3-031-70565-6</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:24:31Z","timestamp":1725150271755},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705656","type":"print"},{"value":"9783031705663","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70566-3_24","type":"book-chapter","created":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:29:51Z","timestamp":1725143391000},"page":"275-287","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint-Average Mean and Variance Feature Matching (JAMVFM) Semi-supervised GAN with Additional-Objective Training Function for Intent Detection"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-4713-5047","authenticated-orcid":false,"given":"Ankit","family":"Kumar","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5542-149X","authenticated-orcid":false,"given":"Munir","family":"Georges","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,27]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Bastianelli, E., Vanzo, A., Swietojanski, P., Rieser, V.: SLURP: a spoken language understanding resource package. arXiv preprint arXiv:2011.13205 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"24_CR2","unstructured":"Benazir, A., Xu, Z., Lin, F.X.: Leveraging cache to enable SLU on tiny devices. arXiv preprint arXiv:2311.18188 (2023)"},{"key":"24_CR3","unstructured":"Chen, Q., Zhuo, Z., Wang, W.: BERT for joint intent classification and slot filling. arXiv preprint arXiv:1902.10909 (2019)"},{"key":"24_CR4","unstructured":"Coucke, A., et\u00a0al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Croce, D., Castellucci, G., Basili, R.: Gan-BERT: generative adversarial learning for robust text classification with a bunch of labeled examples (2020)","DOI":"10.18653\/v1\/2020.acl-main.191"},{"key":"24_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Goo, C.W., et al.: Slot-gated modeling for joint slot filling and intent prediction. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 753\u2013757 (2018)","DOI":"10.18653\/v1\/N18-2118"},{"key":"24_CR8","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Hasan, M., Basher, M.J.I., Shawon, M.T.R.: Bengali intent classification with generative adversarial Bert. In: 2023 26th International Conference on Computer and Information Technology (ICCIT), pp.\u00a01\u20136. IEEE (2023)","DOI":"10.1109\/ICCIT60459.2023.10440989"},{"issue":"4","key":"24_CR10","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TCDS.2018.2875462","volume":"11","author":"C Hu","year":"2018","unstructured":"Hu, C., Wu, X.J., Kittler, J.: Semi-supervised learning based on GAN with mean and variance feature matching. IEEE Trans. Cognit. Dev. Syst. 11(4), 539\u2013547 (2018)","journal-title":"IEEE Trans. Cognit. Dev. Syst."},{"key":"24_CR11","unstructured":"K, A.: Spoken language understanding by generative adversarial network with repulsive loss function on limited data. submission to Interspeech (2024)"},{"key":"24_CR12","unstructured":"Kendrick, C., Frohnmaier, M., Georges, M.: Audio-visual recipe guidance for smart kitchen devices. In: Proceedings of the 4th International Conference on Natural Language and Speech Processing (ICNLSP 2021), pp. 257\u2013261 (2021)"},{"key":"24_CR13","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"24_CR14","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"24_CR15","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Liu, P., Qiu, X., Huang, X.: Adversarial multi-task learning for text classification. arXiv preprint arXiv:1704.05742 (2017)","DOI":"10.18653\/v1\/P17-1001"},{"key":"24_CR17","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"24_CR18","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"24_CR19","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Ravuri, S., Stolcke, A.: Recurrent neural network and LSTM models for lexical utterance classification. In: Sixteenth aNnual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-42"},{"key":"24_CR21","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"24_CR22","unstructured":"Stemmer, G., et\u00a0al.: Speech recognition and understanding on hardware-accelerated DSP. In: Interspeech, pp. 2036\u20132037 (2017)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Tur, G., Hakkani-T\u00fcr, D., Heck, L.: What is left to be understood in Atis? In: 2010 IEEE Spoken Language Technology Workshop, pp. 19\u201324. IEEE (2010)","DOI":"10.1109\/SLT.2010.5700816"},{"key":"24_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"24_CR25","unstructured":"Wang, W., Sun, Y., Halgamuge, S.: Improving MMD-GAN training with repulsive loss function. arXiv preprint arXiv:1812.09916 (2018)"},{"key":"24_CR26","unstructured":"Yang, Z., Cohen, W., Salakhudinov, R.: Revisiting semi-supervised learning with graph embeddings. In: International Conference on Machine Learning, pp. 40\u201348. PMLR (2016)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Are pretrained transformers robust in intent classification? A missing ingredient in evaluation of out-of-scope intent detection. arXiv preprint arXiv:2106.04564 (2021)","DOI":"10.18653\/v1\/2022.nlp4convai-1.2"},{"key":"24_CR28","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, Z., Lu, K., Pan, Q., Li, Y.: A sea-land clutter classification framework for over-the-horizon-radar based on weighted loss semi-supervised GAN. arXiv preprint arXiv:2305.04021 (2023)","DOI":"10.1016\/j.engappai.2024.108526"},{"key":"24_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119164","volume":"213","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z., Cai, Y., Gong, W.: Semi-supervised learning with graph convolutional extreme learning machines. Expert Syst. Appl. 213, 119164 (2023)","journal-title":"Expert Syst. Appl."}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70566-3_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:32:00Z","timestamp":1725143520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70566-3_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705656","9783031705663"],"references-count":30,"URL":"http:\/\/dx.doi.org\/10.1007\/978-3-031-70566-3_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"27 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}</enrichment>
    <enrichment key="local_crossrefDocumentType">book-chapter</enrichment>
    <enrichment key="local_crossrefLicence">https://www.springernature.com/gp/researchers/text-and-data-mining</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorIdentifierOrcid_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorIdentifierOrcid_2,PublisherName,PublisherPlace,TitleMain_1,Language,TitleParent_1,PageNumber,PageFirst,PageLast,CompletedYear,IdentifierIsbn,IdentifierIssn,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1007/978-3-031-70566-3_24</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_conferenceName">27th International Conference on Text, Speech and Dialogue (TSD 2024), Brno (Czech Republic), 09.-13.09.2024</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Ankit</first_name>
      <last_name>Kumar</last_name>
    </author>
    <editor>
      <first_name>Elmar</first_name>
      <last_name>Nöth</last_name>
    </editor>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <editor>
      <first_name>Aleš</first_name>
      <last_name>Horák</last_name>
    </editor>
    <editor>
      <first_name>Petr</first_name>
      <last_name>Sojka</last_name>
    </editor>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>5058</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>3</pageFirst>
    <pageLast>12</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Cham</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2024-09-02</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Retrieval Augmented Spoken Language Generation for Transport Domain</title>
    <parentTitle language="eng">Text, Speech, and Dialogue: 27th International Conference, TSD 2024 Brno, Czech Republic, September 9–13, 2024 Proceedings, Part II</parentTitle>
    <identifier type="isbn">978-3-031-70566-3</identifier>
    <identifier type="isbn">978-3-031-70565-6</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:24:41Z","timestamp":1725150281661},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705656","type":"print"},{"value":"9783031705663","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70566-3_1","type":"book-chapter","created":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:29:51Z","timestamp":1725143391000},"page":"3-12","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Retrieval Augmented Spoken Language Generation for\u00a0Transport Domain"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0009-0001-6459-7630","authenticated-orcid":false,"given":"Gokul","family":"Srinivasagan","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5542-149X","authenticated-orcid":false,"given":"Munir","family":"Georges","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,27]]},"reference":[{"key":"1_CR1","unstructured":"Abdullin, Y., Molla-Aliod, D., Ofoghi, B., Yearwood, J., Li, Q.: Synthetic dialogue dataset generation using LLM agents (2024). arXiv preprint arXiv:2401.17461"},{"key":"1_CR2","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., Hajishirzi, H.: Self-RAG: Learning to retrieve, generate, and critique through self-reflection (2023). arXiv preprint arXiv:2310.11511"},{"key":"1_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, 12449\u201312460 (2020)"},{"key":"1_CR4","unstructured":"Barrault, L., et al.: SeamlessM4T-massively multilingual &amp; multimodal machine translation (2023). arXiv preprint arXiv:2308.11596"},{"key":"1_CR5","unstructured":"Borgeaud, S., et\u00a0al.: Improving language models by retrieving from trillions of tokens. In: International Conference on Machine Learning, pp. 2206\u20132240. PMLR (2022)"},{"key":"1_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Chiang, C.H., Lee, H.Y.: Can large language models be an alternative to human evaluations? In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15607\u201315631. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.870, https:\/\/aclanthology.org\/2023.acl-long.870","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"1_CR8","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: International Conference on Machine Learning, pp. 3929\u20133938. PMLR (2020)"},{"key":"1_CR9","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"1_CR10","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7B (2023). arXiv preprint arXiv:2310.06825"},{"key":"1_CR11","unstructured":"Kandpal, N., Deng, H., Roberts, A., Wallace, E., Raffel, C.: Large language models struggle to learn long-tail knowledge. In: International Conference on Machine Learning, pp. 15696\u201315707. PMLR (2023)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering (2020). arXiv preprint arXiv:2004.04906","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"1_CR13","unstructured":"Labrak, Y., Bazoge, A., Morin, E., Gourraud, P.A., Rouvier, M., Dufour, R.: BioMistral: A collection of open-source pretrained large language models for medical domains (2024). arXiv preprint arXiv:2402.10373"},{"key":"1_CR14","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"1_CR15","unstructured":"Peng, R., Liu, K., Yang, P., Yuan, Z., Li, S.: Embedding-based retrieval with LLM for effective agriculture information extracting from unstructured data (2023). arXiv preprint arXiv:2308.03107"},{"key":"1_CR16","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"1_CR17","unstructured":"Scao, T.L., et\u00a0al.: Bloom: A 176b-parameter open-access multilingual language model (2022). arXiv preprint arXiv:2211.05100"},{"key":"1_CR18","unstructured":"Sinitsin, A., Plokhotnyuk, V., Pyrkin, D., Popov, S., Babenko, A.: Editable neural networks (2020). arXiv preprint arXiv:2004.00345"},{"key":"1_CR19","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models (2023). arXiv preprint arXiv:2312.11805"},{"key":"1_CR20","unstructured":"Touvron, H., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models (2023). arXiv preprint arXiv:2307.09288"},{"key":"1_CR21","unstructured":"Tunstall, L., et\u00a0al.: Zephyr: Direct distillation of LM alignment (2023). arXiv preprint arXiv:2310.16944"},{"key":"1_CR22","unstructured":"Wang, X., et al.: KnowledGPT: Enhancing large language models with retrieval and storage access on knowledge bases (2023). arXiv preprint arXiv:2308.11761"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70566-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:30:04Z","timestamp":1725143404000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70566-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705656","9783031705663"],"references-count":22,"URL":"http:\/\/dx.doi.org\/10.1007\/978-3-031-70566-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"27 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}</enrichment>
    <enrichment key="local_crossrefDocumentType">book-chapter</enrichment>
    <enrichment key="local_crossrefLicence">https://www.springernature.com/gp/researchers/text-and-data-mining</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorIdentifierOrcid_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorIdentifierOrcid_2,PublisherName,PublisherPlace,TitleMain_1,Language,TitleParent_1,PageNumber,PageFirst,PageLast,CompletedYear,IdentifierIsbn,IdentifierIssn,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1007/978-3-031-70566-3_1</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_conferenceName">27th International Conference on Text, Speech and Dialogue (TSD 2024), Brno (Czech Republic), 09.-13.09.2024</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Gokul</first_name>
      <last_name>Srinivasagan</last_name>
    </author>
    <editor>
      <first_name>Elmar</first_name>
      <last_name>Nöth</last_name>
    </editor>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <editor>
      <first_name>Aleš</first_name>
      <last_name>Horák</last_name>
    </editor>
    <editor>
      <first_name>Petr</first_name>
      <last_name>Sojka</last_name>
    </editor>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
  </doc>
  <doc>
    <id>5108</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>133</pageFirst>
    <pageLast>140</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>Gesellschaft für Informatik</publisherName>
    <publisherPlace>Bonn</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2024-09-12</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">A Multidisciplinary Approach to AI-based self-motivated Learning and Teaching with Large Language Models</title>
    <abstract language="eng">We present a learning experience platform that uses machine learning methods to support students and lecturers in self-motivated online learning and teaching processes. The platform is being developed as an agile open-source collaborative project supported by multiple universities and partners. The development is guided didactically, reviewed, and scientifically evaluated in several cycles. Transparency, data protection and the copyright compliant use of the system is a central part of the project. The system further employs large language models (LLMs). Due to privacy concerns, we utilize locally hosted LLM instances and explicitly do not rely on available cloud products. Students and lecturers can interact with an LLM-based chatbot in the current prototype. The AI-generated outputs contain cross-references to the current educational video’s context, indicating if sections are based on the lectures context or world knowledge. We present the prototype and results of our qualitative evaluation from the perspective of lecturers and students.</abstract>
    <parentTitle language="deu">DELFI 2024, Die 22. Fachtagung Bildungstechnologien der Gesellschaft für Informatik e.V.</parentTitle>
    <identifier type="isbn">978-3-88579-255-0</identifier>
    <identifier type="urn">urn:nbn:de:bvb:573-51089</identifier>
    <enrichment key="THI_openaccess">ja</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.18420/delfi2024_11</enrichment>
    <enrichment key="THI_conferenceName">22. Fachtagung Bildungstechnologien der Gesellschaft für Informatik e.V. (DELFI 2024), Fulda (Germany), 09.-11.09.2024</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Creative Commons BY-SA 4.0</licence>
    <author>
      <first_name>Thomas</first_name>
      <last_name>Ranzenberger</last_name>
    </author>
    <editor>
      <first_name>Sandra</first_name>
      <last_name>Schulz</last_name>
    </editor>
    <author>
      <first_name>Carolin</first_name>
      <last_name>Freier</last_name>
    </author>
    <editor>
      <first_name>Natalie</first_name>
      <last_name>Kiesler</last_name>
    </editor>
    <author>
      <first_name>Luca</first_name>
      <last_name>Reinold</last_name>
    </author>
    <author>
      <first_name>Korbinian</first_name>
      <last_name>Riedhammer</last_name>
    </author>
    <author>
      <first_name>Fabian</first_name>
      <last_name>Schneider</last_name>
    </author>
    <author>
      <first_name>Christopher</first_name>
      <last_name>Simic</last_name>
    </author>
    <author>
      <first_name>Claudia</first_name>
      <last_name>Simon</last_name>
    </author>
    <author>
      <first_name>Steffen</first_name>
      <last_name>Freisinger</last_name>
    </author>
    <author>
      <first_name>Munir</first_name>
      <last_name>Georges</last_name>
    </author>
    <author>
      <first_name>Tobias</first_name>
      <last_name>Bocklet</last_name>
    </author>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <collection role="persons" number="40770">Georges, Munir</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-haw/files/5108/Thomas-Ranzenberger.pdf</file>
  </doc>
</export-example>
