TY - CHAP A1 - Stemmer, Georg A1 - Georges, Munir A1 - Hofer, Joachim A1 - Rozen, Piotr A1 - Bauer, Josef A1 - Nowicki, Jakub A1 - Bocklet, Tobias A1 - Colett, Hannah R. A1 - Falik, Ohad A1 - Deisher, Michael A1 - Downing, Sylvia J. T1 - Speech Recognition and Understanding on Hardware-Accelerated DSP T2 - Proceedings Interspeech 2017 UR - https://doi.org/10.21437/Interspeech.2017 KW - speech recognition KW - natural language understanding KW - neural network hardware Y1 - 2017 UR - https://doi.org/10.21437/Interspeech.2017 UR - https://www.isca-speech.org/archive/interspeech_2017/stemmer17_interspeech.html SP - 2036 EP - 2037 PB - International Speech Communication Association (ISCA) CY - Baixas ER - TY - CHAP A1 - Chen, Liu A1 - Deisher, Michael A1 - Georges, Munir T1 - An End-to-End Neural Network for Image-to-Audio Transformation T2 - Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) UR - https://doi.org/10.1109/ICASSP49357.2023.10096121 KW - OCR KW - TTS KW - image-to-speech Y1 - 2023 UR - https://doi.org/10.1109/ICASSP49357.2023.10096121 SN - 978-1-7281-6327-7 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Georges, Munir A1 - Kanthak, Stephan A1 - Klakow, Dietrich T1 - Accurate client-server based speech recognition keeping personal data on the client T2 - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) UR - https://doi.org/10.1109/ICASSP.2014.6854205 KW - Dynamic Language Model KW - Acoustic Filler KW - Data Privacy KW - Client-Server Speech Recognition Y1 - 2014 UR - https://doi.org/10.1109/ICASSP.2014.6854205 SN - 978-1-4799-2893-4 SN - 2379-190X SN - 1520-6149 SP - 3271 EP - 3275 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Georges, Munir A1 - Kanthak, Stephan A1 - Klakow, Dietrich T1 - Transducer-based speech recognition with dynamic language models T2 - Proceedings Interspeech 2013 UR - doi.org/10.21437/Interspeech.2013-185 KW - embedded speech recognition KW - embedded grammars KW - Markov language models KW - transducer nesting Y1 - 2013 UR - doi.org/10.21437/Interspeech.2013-185 SP - 642 EP - 646 PB - International Speech Communication Association (ISCA) CY - Baixas ER - TY - CHAP A1 - Herygers, Aaricia A1 - Verkhodanova, Vass A1 - Coler, Matt A1 - Scharenborg, Odette A1 - Georges, Munir ED - Draxler, Christoph T1 - Bias in Flemish Automatic Speech Recognition T2 - Elektronische Sprachsignalverarbeitung 2023: Tagungsband der 34. Konferenz München, 1.-3. März 2023 KW - Automatic speech recognition KW - Bias Y1 - 2023 UR - https://www.essv.de/paper.php?id=1186 SN - 978-3-95908-303-4 SP - 158 EP - 165 PB - TUDpress CY - Dresden ER - TY - CHAP A1 - Kendrick, Caroline A1 - Frohnmaier, Mariano A1 - Georges, Munir T1 - Audio-Visual Recipe Guidance for Smart Kitchen Devices T2 - ICNLSP 2021: Proceedings of the 4th International Conference on Natural Language and Speech Processing UR - https://aclanthology.org/2021.icnlsp-1.30 Y1 - 2021 UR - https://aclanthology.org/2021.icnlsp-1.30 SN - 978-1-955917-18-6 SP - 257 EP - 261 PB - ACL CY - Stroudsburg ER - TY - CHAP A1 - Georges, Munir A1 - Czarnowski, Krzysztof A1 - Bocklet, Tobias T1 - Ultra-Compact NLU BT - Neuronal Network Binarization as Regularization T2 - Proceedings Interspeech 2019 UR - https://doi.org/10.21437/Interspeech.2019-2591 KW - ASR KW - NLU KW - SLU KW - binary DNN KW - regularization Y1 - 2019 UR - https://doi.org/10.21437/Interspeech.2019-2591 SP - 809 EP - 813 PB - ISCA CY - Baixas ER - TY - CHAP A1 - Hartung, Kai A1 - Herygers, Aaricia A1 - Kurlekar, Shubham Vijay A1 - Zakaria, Khabbab A1 - Volkan, Taylan A1 - Gröttrup, Sören A1 - Georges, Munir ED - Ekštein, Kamil ED - Pártl, František ED - Konopík, Miloslav T1 - Measuring Sentiment Bias in Machine Translation T2 - Text, Speech, and Dialogue: 26th International Conference: Proceedings UR - https://doi.org/10.1007/978-3-031-40498-6_8 KW - Machine translation KW - sentiment classification KW - bias Y1 - 2023 UR - https://doi.org/10.1007/978-3-031-40498-6_8 SN - 978-3-031-40498-6 SN - 1611-3349 SP - 82 EP - 93 PB - Springer CY - Cham ER - TY - CHAP A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Georges, Munir T1 - Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes T2 - INTERSPEECH 2023 UR - https://doi.org/10.21437/Interspeech.2023-772 KW - speech recognition KW - cross-lingual KW - zero-shot KW - phoneme recognition Y1 - 2023 UR - https://doi.org/10.21437/Interspeech.2023-772 N1 - „Der Nachweis einer Preprint-Version dieser Veröffentlichung ist ebenfalls in diesem Repositorium verzeichnet, s. https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/3730" SP - 2258 EP - 2262 PB - ISCA CY - Baixas ER - TY - CHAP A1 - Srinivasagan, Gokul A1 - Deisher, Michael A1 - Georges, Munir T1 - Compression of end-to-end non-autoregressive image-to-speech system for lowresourced devices T2 - Speech Communication, 15th ITG Conference, 20.-22.09.2023 in Aachen, Germany UR - https://doi.org/10.30420/456164029 Y1 - 2023 UR - https://doi.org/10.30420/456164029 SN - 978-3-8007-6164-7 SN - 978-3-8007-6165-4 N1 - Auch veröffentlicht auf IEEE: https://ieeexplore.ieee.org/document/10363017 N1 - Der Nachweis einer Preprint-Version dieser Veröffentlichung ist ebenfalls in diesem Repositorium verzeichnet, s. https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/4611 SP - 151 EP - 155 PB - VDE Verlag CY - Berlin ER - TY - CHAP A1 - Ranzenberger, Thomas A1 - Bocklet, Tobias A1 - Freisinger, Steffen A1 - Frischholz, Lia A1 - Georges, Munir A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Peinl, René A1 - Riedhammer, Korbinian A1 - Schneider, Fabian A1 - Simic, Christopher A1 - Zakaria, Khabbab ED - Draxler, Christoph T1 - The Hochschul-Assistenz-System HAnS: An ML-Based Learning Experience Platform T2 - Elektronische Sprachsignalverarbeitung 2023: Tagungsband der 34. Konferenz München, 1.-3. März 2023 Y1 - 2023 UR - https://www.essv.de/paper.php?id=1188 SN - 978-3-95908-303-4 SP - 168 EP - 169 PB - TUDpress CY - Dresden ER - TY - CHAP A1 - Freisinger, Steffen A1 - Schneider, Fabian A1 - Herygers, Aaricia A1 - Georges, Munir A1 - Bocklet, Tobias A1 - Riedhammer, Korbinian T1 - Unsupervised Multilingual Topic Segmentation of Video Lectures: What can Hierarchical Labels tell us about the Performance? T2 - Proceedings 9th Workshop on Speech and Language Technology in Education (SLaTE) UR - https://doi.org/10.21437/SLaTE.2023-27 KW - topic segmentation KW - video lectures KW - hierarchical topics KW - multilingual Y1 - 2023 UR - https://doi.org/10.21437/SLaTE.2023-27 SP - 141 EP - 145 PB - International Speech Communication Association (ISCA) CY - Baixas ER - TY - CHAP A1 - Hartung, Kai A1 - Jäger, Gerhard A1 - Gröttrup, Sören A1 - Georges, Munir ED - Vylomova, Ekaterina ED - Ponti, Edoardo ED - Cotterell, Ryan T1 - Typological Word Order Correlations with Logistic Brownian Motion T2 - Proceedings of the 4th Workshop on Computational Typology and Multilingual NLP (SIGTYP 2022) N2 - In this study we address the question to what extent syntactic word-order traits of different languages have evolved under correlation and whether such dependencies can be found universally across all languages or restricted to specific language families.To do so, we use logistic Brownian Motion under a Bayesian framework to model the trait evolution for 768 languages from 34 language families. We test for trait correlations both in single families and universally over all families. Separate models reveal no universal correlation patterns and Bayes Factor analysis of models over all covered families also strongly indicate lineage specific correlation patters instead of universal dependencies. KW - Typology KW - Brownian Motion Y1 - 2022 UR - https://aclanthology.org/2022.sigtyp-1.3 SN - 978-1-955917-93-3 SP - 22 EP - 26 PB - Association for Computational Linguistics CY - Stroudsburg ER - TY - INPR A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Georges, Munir T1 - Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes N2 - This paper proposes Allophant, a multilingual phoneme recognizer. It requires only a phoneme inventory for crosslingual transfer to a target language, allowing for low-resource recognition. The architecture combines a compositional phone embedding approach with individually supervised phonetic attribute classifiers in a multi-task architecture. We also introduce Allophoible, an extension of the PHOIBLE database. When combined with a distance based mapping approach for grapheme-to-phoneme outputs, it allows us to train on PHOIBLE inventories directly. By training and evaluating on 34 languages, we found that the addition of multi-task learning improves the model’s capability of being applied to unseen phonemes and phoneme inventories. On supervised languages we achieve phoneme error rate improvements of 11 percentage points (pp.) compared to a baseline without multi-task learning. Evaluation of zero-shot transfer on 84 languages yielded a decrease in PER of 2.63 pp. over the baseline. UR - https://doi.org/10.48550/arXiv.2306.04306 KW - speech recognition KW - cross-lingual KW - zero-shot KW - phoneme recognition Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2306.04306 N1 - „Die veröffentlichte Version dieses Preprints ist ebenfalls in diesem Repositorium verzeichnet, s.https://opus4.kobv.de/opus4-haw/admin/document/edit/id/3923" PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Georges, Munir A1 - Huang, Jonathan A1 - Bocklet, Tobias T1 - Compact Speaker Embedding: lrx-vector T2 - Proceedings Interspeech 2020 UR - https://doi.org/10.21437/Interspeech.2020-2106 KW - speaker recognition KW - x-vector KW - low power Y1 - 2020 UR - https://doi.org/10.21437/Interspeech.2020-2106 SP - 3236 EP - 3240 PB - ISCA CY - [s. l.] ER - TY - INPR A1 - Pagonis, Panagiotis A1 - Hartung, Kai A1 - Wu, Di A1 - Georges, Munir A1 - Gröttrup, Sören T1 - Analysis of Knowledge Tracing performance on synthesised student data N2 - Knowledge Tracing (KT) aims to predict the future performance of students by tracking the development of their knowledge states. Despite all the recent progress made in this field, the application of KT models in education systems is still restricted from the data perspectives: 1) limited access to real life data due to data protection concerns, 2) lack of diversity in public datasets, 3) noises in benchmark datasets such as duplicate records. To resolve these problems, we simulated student data with three statistical strategies based on public datasets and tested their performance on two KT baselines. While we observe only minor performance improvement with additional synthetic data, our work shows that using only synthetic data for training can lead to similar performance as real data. UR - https://doi.org/10.48550/arXiv.2401.16832 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2401.16832 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-44771 N1 - Die veröffentlichte Version dieses Preprints ist ebenfalls in diesem Repositorium verzeichnet, s. https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/4535 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Pagonis, Panagiotis A1 - Hartung, Kai A1 - Wu, Di A1 - Georges, Munir A1 - Gröttrup, Sören T1 - Analysis of Knowledge Tracing performance on synthesised student data Y1 - 2024 UR - https://sme.uni-bamberg.de/ai4ai/ N1 - Der Nachweis einer Preprint-Version dieser Veröffentlichung ist ebenfalls in diesem Repositorium verzeichnet, s. https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/4477 PB - Universität Bamberg CY - Bamberg ER - TY - CHAP A1 - Glocker, Kevin A1 - Georges, Munir T1 - Hierarchical Multi-Task Transformers for Crosslingual Low Resource Phoneme Recognition T2 - Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022) N2 - 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. 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. KW - speech recognition KW - multilingual KW - zero-shot KW - multi-task learning Y1 - 2022 UR - https://aclanthology.org/2022.icnlsp-1.21 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-30544 SN - 978-1-959429-36-4 SP - 187 EP - 192 PB - Association for Computational Linguistics CY - Stroudsburg ER - TY - CHAP A1 - Glocker, Kevin A1 - Georges, Munir ED - Abbas, Mourad T1 - Hierarchical Multi-task Learning with Articulatory Attributes for Cross-Lingual Phoneme Recognition T2 - Practical Solutions for Diverse Real-World NLP Applications UR - https://doi.org/10.1007/978-3-031-44260-5_4 Y1 - 2023 UR - https://doi.org/10.1007/978-3-031-44260-5_4 SN - 978-3-031-44259-9 SN - 978-3-031-44260-5 SP - 59 EP - 75 PB - Springer CY - Cham ER - TY - CHAP A1 - Ranzenberger, Thomas A1 - Bocklet, Tobias A1 - Freisinger, Steffen A1 - Georges, Munir A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Riedhammer, Korbinian A1 - Schneider, Fabian A1 - Simic, Christopher A1 - Zakaria, Khabbab ED - Baumann, Timo T1 - Extending HAnS: Large Language Models for Question Answering, Summarization, and Topic Segmentation in an ML-based Learning Experience Platform T2 - Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024 UR - https://doi.org/10.35096/othr/pub-7103 KW - hans KW - learning experience platform KW - speech processing KW - natural language processing KW - large language models Y1 - 2024 UR - https://doi.org/10.35096/othr/pub-7103 SN - 978-3-95908-325-6 SP - 219 EP - 224 PB - TUDPress CY - Dresden ER -