<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>261</id>
    <completedYear>2014</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>VDE VERLAG GMBH</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Semi-Automatic Calibration for Dereverberation by Spectral Subtraction for Continuous Speech Recognition</title>
    <abstract language="eng">In this article, we describe a semi-automatic calibration algorithm for dereverberation by spectral subtraction. We verify the method by a comparison to a manual calibration derived from measured room impulse responses (RIR). We conduct extensive experiments to understand the effect of all involved parameters and to verify values suggested in the literature. The experiments are performed on a text read by 31 speakers and recorded by a headset and three far-field microphones. Results are measured in terms of automatic speech recognition (ASR) performance using a 1-gram model to emphasize acoustic recognition performance. To accommodate for the acoustic change by dereverberation we apply supervised MAP adaptation to the hidden Markov model output probabilities. The combination of dereverberation and adaptation yields a relative improvement of about 35% in terms of word error rate (WER) compared to the original signal.</abstract>
    <parentTitle language="eng">ITG Symposium on Speech Communication 2014, Erlangen.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <author>Tobias Bocklet</author>
    <author>Juan Rafael Orozco-Arroyave</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>264</id>
    <completedYear>2013</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">The Tao of ATWV: Probing the mysteries of keyword search performance</title>
    <abstract language="eng">In this paper we apply diagnostic analysis to gain a deeper understanding of the performance of the the keyword search system that we have developed for conversational telephone speech in the IARPA Babel program. We summarize the Babel task, its primary performance metric, “actual term weighted value” (ATWV), and our recognition and keyword search systems. Our analysis uses two new oracle ATWV measures, a bootstrap-based ATWV confidence interval, and includes a study of the underpinnings of the large ATWV gains due to system combination. This analysis quantifies the potential ATWV gains from improving the number of true hits and the overall quality of the detection scores in our system's posting lists. It also shows that system combination improves our systems' ATWV via a small increase in the number of true hits in the posting lists.</abstract>
    <parentTitle language="eng">IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Olomouc, Czech Republic, Dezember 2013.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Steven Wegmann</author>
    <author>Arlo Faria</author>
    <author>Adam Janin</author>
    <author>Korbinian Riedhammer</author>
    <author>Nelson Morgan</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>266</id>
    <completedYear>2013</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">A Study on LVCSR and Keyword Search for Tagalog</title>
    <abstract language="eng">We describe a state-of-the-art large vocabulary continuous speech recognition (LVCSR) and keyword search (KWS) system trained on roughly 70 hours of conversational telephone speech. Using the Kaldi speech recognition toolkit, we investigate several aspects: for the acoustic front-end, we analyze the use of mel-frequency cepstral coefficients (MFCC), pitch and probability-of-voicing (PoV), and deep neural network (DNN) bottleneck (BN) features, as well as their feature-level combination ("tandem"). For the acousticphonetic decision tree, we explore different hidden Markov model (HMM) topologies for the glottalization phoneme /?/ to model its typically short duration. For the acoustic model, we compare regular continuous HMM with a sort of multi-codebook subspace Gaussian mixture model (SGMM) that lead to an overall best word error rate (WER) of 58.7% and 56.3%, respectively. The KWS is implemented as a word lattice search, and is augmented by a syllable lattice back-up search to capture out-of-vocabulary keywords as well as misrecognized lexical surface forms due to ambiguous prefix and hyphenation rules.</abstract>
    <parentTitle language="eng">INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association (ISCA), Lyon, France, August 2013.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <author>Van Hai Do</author>
    <author>James Hieronymus</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>keyword spotting</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>270</id>
    <completedYear>2012</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>8349</pageFirst>
    <pageLast>8353</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">A Software Kit for Automatic Voice Descrambling</title>
    <abstract language="eng">Voice scrambling is widely used to add privacy to the radio communication of various authorities - but is also used by criminals to evade prosecution. In this article, we consider various analog voice scrambling techniques such as fixed frequency inversion, splitband inversion and rolling code scramblers. We explain how to break them using automatically extracted measures and scoring algorithms, and evaluate the proposed system using simulated data. While the simple inversion can be easily broken, the more advanced techniques require additional work prior to unsupervised automatization; the presented user interface allows the user to refine the automatic results to obtain a high quality solution.</abstract>
    <parentTitle language="eng">2012 IEEE International Conference on Communications (ICC); IEEE International Workshop on Security and Forensics in Communication Systems (SFCS).</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <author>Martin Ring</author>
    <author>Elmar Nöth</author>
    <author>Daniel Kolb</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>272</id>
    <completedYear>2012</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>4213</pageFirst>
    <pageLast>4216</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Generating Exact Lattices in the WFST Framework</title>
    <abstract language="deu">We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alternative transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is “fully expanded”, i.e. where the arcs correspond to HMM transitions. It outputs lattices that include HMM-state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This special determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbol-sequence of A, contains just the lowest-cost path through A.</abstract>
    <parentTitle language="eng">2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, May 2012.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Daniel Povey</author>
    <author>Mirko Hannemann</author>
    <author>Gilles Boulianne</author>
    <author>Lukáš Burget</author>
    <author>Arnab Ghoshal</author>
    <author>Miloš Janda</author>
    <author>Martin Karafiát</author>
    <author>Stefan Kombrink</author>
    <author>Petr Motlíček</author>
    <author>Yanmin Qian</author>
    <author>Korbinian Riedhammer</author>
    <author>Karel Veselý</author>
    <author>Ngoc Thang Vu</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Lattice Generation</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>273</id>
    <completedYear>2011</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">A Novel Lecture Browser Using Key Phrases and Stream Graphs</title>
    <abstract language="deu">We present a novel lecture browser that utilizes ranked key phrases displayed on a stream graph to overcome the shortcomings of traditional extractive (query-based) summaries. The system extracts key phrases from the ASR transcripts, performs an unsupervised ranking, and displays an initial number of phrases on the stream graph. This graph gives an intuition of when which key phrase is spoken, and how dominant it is throughout the lecture. The user can select the phrases to be displayed and furthermore adjust the ranking of the all phrases. All user interactions are logged to a server to improve the ranking algorithms and provide user specific rankings.</abstract>
    <parentTitle language="deu">Lehrstuhl für Mustererkennung, Universität Erlangen-Nürnberg</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <author>Martin Gropp</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>279</id>
    <completedYear>2010</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>4226</pageFirst>
    <pageLast>4229</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Clap Your Hands! Calibrating Spectral Subtraction for Dereverberation</title>
    <abstract language="eng">Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectral subtraction as proposed by Lebart and Boucher and introduce a simple approach to estimate the required decay parameter by clapping hands. Experiments on small vocabulary continuous speech recognition task on read speech show that using the calibrated dereverberation improves WER from 73.2 to 54.7 for the best microphone. In combination with system adaptation, the WER could be reduced to 28.2, which is only a 16% relative loss of performance comparison to using a headset instead of a room microphone.</abstract>
    <parentTitle language="eng">2010 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), Dallas, TX, USA, March 2010.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Uwe Zäh</author>
    <author>Korbinian Riedhammer</author>
    <author>Tobias Bocklet</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>robustness</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>280</id>
    <completedYear>2010</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2420</pageFirst>
    <pageLast>2423</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-03-20</completedDate>
    <publishedDate>2018-06-04</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">FAU IISAH Corpus – A German Speech Database Consisting of Human-Machine and Human-Human Interaction Acquired by Close-Talking and Far-Distance Microphones</title>
    <parentTitle language="eng">7th Conference on International Language Resources and Evaluation (LREC 2010), European Language Resources Association (ELRA), Valletta, Malta,  May 2010.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Werner Spiegl</author>
    <author>Korbinian Riedhammer</author>
    <author>Stefan Steidl</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>281</id>
    <completedYear>2009</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2015</pageFirst>
    <pageLast>2018</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation>ACM New York, NY, USA ©2009</creatingCorporation>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Towards a Language-independent Intelligibility Assessment of Children with Cleft Lip and Palate</title>
    <abstract language="eng">We describe a novel evaluation system for the intelligibility assessment of children with CLP on standardized tests. The system is solely based on standard cepstral features in form of MFCCs. No other information like word alignments is used. So the system can be easily adapted to other languages. For each child one GMM is created by adaptation of a UBM to the speaker-specific MFCCs. The components of this GMM are concatenated in order to create a so-called GMM supervector. These GMM supervectors are then used as meta features for an SVR. We evaluated our language-independent system on two different datasets of children suffering from CLP. One dataset contains recordings of 35 German children, where the children named different pictograms. The other dataset contains recordings of 14 Italian speaking children, who repeated standardized sentences. On both datasets we achieved high correlations: up to 0.81 for the German dataset and 0.83 for the Italian dataset.</abstract>
    <parentTitle language="eng">WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Tobias Bocklet</author>
    <author>Andreas Maier</author>
    <author>Korbinian Riedhammer</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>282</id>
    <completedYear>2016</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation>2016 ISCA</creatingCorporation>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">REMEETING: Searchable Conversations</title>
    <parentTitle language="eng">INTERSPEECH 2016, Annual Conference of the International Speech Communication Association (ISCA), IEEE Workshop on Spoken Language Technologies (SLT), San Francisco, USA, September 2016.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Arlo Faria</author>
    <author>Korbinian Riedhammer</author>
    <author>Adam Janin</author>
    <author>A. Bauer</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>283</id>
    <completedYear>2015</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">REMEETING — Get More Out Of Meetings</title>
    <abstract language="eng">Remeeting is a tool that helps you get more out of in-person&#13;
meetings. Calendar integration and a special email address allow&#13;
users to email agenda items prior to a certain meeting. A&#13;
discrete notification at the time of the meeting reminds the user&#13;
to start the recording. During the meeting, the user focuses on the conversation, or can add notes and photos if desired. After the meeting, every participant gets notified by an automated email that lists the participants along with automatically extracted keywords, notes and photos. This stimulates collaboration, and keeps follow-up contributions at a central place: Just reply to add further notes to the meeting. The resulting meeting “document” can be shared with others and reviewed using a web app that acts as a visual index to the meeting. This makes Remeeting the perfect tool for regular group meetings, standups and interviews, where people typically track progress and follow up on. Remeeting is leveraging, promoting and contributing to open source projects including kaldi and docker.</abstract>
    <parentTitle language="eng">INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 2015.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Arlo Faria</author>
    <author>Korbinian Riedhammer</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speaker identification</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>automatic summarization</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>productivity</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>284</id>
    <completedYear>2014</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">REMEETING — Get More Out of Meetings</title>
    <parentTitle language="eng">INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, IEEE Workshop on Spoken Language Technologies (SLT), Singapore, September 2014.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Arlo Faria</author>
    <author>Korbinian Riedhammer</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speaker identification</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>automatic summarization</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>productivity</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>288</id>
    <completedYear>2008</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>69</pageFirst>
    <pageLast>72</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">The CALO Meeting Speech Recognition and Understanding System</title>
    <abstract language="eng">The CALO meeting assistant provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item recognition, decision extraction, and summarization.</abstract>
    <parentTitle language="eng">2008 IEEE Workshop on Spoken Language Technologies (SLT),  Goa, India, December 2008.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Gokhan Tur</author>
    <author>Andreas Stolcke</author>
    <author>Lynn Voss</author>
    <author>John Dowding</author>
    <author>Benoit Favre</author>
    <author>Raquel Fernandez</author>
    <author>Matthew Frampton</author>
    <author>Michael Frandsen</author>
    <author>Clive Frederickson</author>
    <author>Martin Graciarena</author>
    <author>Dilek Hakkani-Tür</author>
    <author>Donald Kintzing</author>
    <author>Kyle Leveque</author>
    <author>Shane Mason</author>
    <author>John Niekrasz</author>
    <author>Stanley Peters</author>
    <author>Matthew Purver</author>
    <author>Korbinian Riedhammer</author>
    <author>Elizabeth Shriberg</author>
    <author>Jing Tien</author>
    <author>Dimitra Vergyri</author>
    <author>Fan Yang</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>multiparty meetings processing</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>spoken language understanding</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>294</id>
    <completedYear>2006</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>17</pageFirst>
    <pageLast>22</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Automatic Evaluation of Tracheoesophageal Telephone Speech</title>
    <abstract language="eng">The tracheoesophageal (TE) substitute voice is currently state–of–the–art treatment to restore the ability to speak after laryngectomy. The intelligibility while talking over a telephone is an important clinical factor, as it is a crucial part of the patients’ social life. An objective way to rate the intelligibility of substitute voices when talking over a telephone is desirable to improve the post–laryngectomy speech therapy. An automatic speech recognition (ASR) system was applied to 41 high quality recordings of post–laryngectomy patients. The ASR system was trained with normal, non–pathologic speech. It yielded a word accuracy (WA) of 36.9%±18.0%; compared to the intelligibility rating of a group of human experts the ASR system had a correlation coefﬁcient of -.88. After downsampling the 41 recordings to telephone quality, the ASR system reached a WA of 26.4%±13.9% leading to a correlation coefﬁcient of -.80. These results conﬁrm that an ASR system can be used for objective intelligibility rating over the telephone.</abstract>
    <parentTitle language="eng">First International Language Technologies Conference (IS-LTC 2006), Ljubljana, Slovenia, October 2006.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <author>Tino Haderlein</author>
    <author>Maria Schuster</author>
    <author>Frank Rosanowski</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>296</id>
    <completedYear>2012</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>book</type>
    <publisherName>Logos Verlag Berlin GmbH</publisherName>
    <publisherPlace>Berlin</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Interactive Approaches to Video Lecture Assessment</title>
    <abstract language="eng">Folks that have been here last winter prior to ASRU might be familiar with the title of that talk. But don't be misled, I'll have something new for you. In this talk, I will give an overview over the FAU Lecture Browser which I developed in the context of my thesis. I will start out with the description of a novel data set: The LME Lectures are a corpus of two series of graduate level computer science lectures with 18 recordings each. The courses cover topics in medical image processing and pattern analysis/machine learning. The roughly 40 hours of speech were manually transcribed, and one particular lecture was annotated with key phrases by five human raters. Using this data set, I trained three different speech recognizers using regular continuous, multi-codebook semi-continuous and subspace Gaussian mixture models, that show an error rate of about 10% WER. I will then briefly describe the key phrase extraction and automatic ranking, which was then compared against five raters on one lecture recording. Finally, I will talk about a little usability study where 10 students were asked to perform a certain task-- with and without the proposed lecture browser. Although the number of contestants is limited, the numbers are interesting: the users that had the interface could complete the tasks about 30% faster than the control group, while maintaining about the same accuracy.</abstract>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>297</id>
    <completedYear>2008</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>book</type>
    <publisherName>Mueller Verlag</publisherName>
    <publisherPlace>Nürnberg</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">An Automatic Intelligibility Test Based on the Post-Laryngectomy Telephone Test</title>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>307</id>
    <completedYear>2012</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>390</pageFirst>
    <pageLast>397</pageLast>
    <pageNumber/>
    <edition/>
    <issue>26(3)</issue>
    <volume/>
    <type>contributiontoperiodical</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Automatic Intelligibility Assessment of Speakers After Laryngeal Cancer by Means of Acoustic Modeling</title>
    <abstract language="eng">One aspect of voice and speech evaluation after laryngeal cancer is acoustic analysis. Perceptual evaluation by expert raters is a standard in the clinical environment for global criteria such as overall quality or intelligibility. So far, automatic approaches evaluate acoustic properties of pathologic voices based on voiced/unvoiced distinction and fundamental frequency analysis of sustained vowels. Because of the high amount of noisy components and the increasing aperiodicity of highly pathologic voices, a fully automatic analysis of fundamental frequency is difficult. We introduce a purely data-driven system for the acoustic analysis of pathologic voices based on recordings of a standard text.</abstract>
    <parentTitle language="eng">Journal of Voice</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Tobias Bocklet</author>
    <author>Korbinian Riedhammer</author>
    <author>Elmar Nöth</author>
    <author>Ulrich Eysholdt</author>
    <author>Tino Haderlein</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Lung cancer technologies</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>308</id>
    <completedYear>2010</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>801</pageFirst>
    <pageLast>815</pageLast>
    <pageNumber/>
    <edition/>
    <issue>52(10)</issue>
    <volume>2010</volume>
    <type>contributiontoperiodical</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Long story short - Global unsupervised models for keyphrase based meeting summarization</title>
    <parentTitle language="eng">SPEECH COMMUNICATION</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <author>Benoit Favre</author>
    <author>Dilek Hakkani-Tür</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Meeting Summarization</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
</export-example>
