@inproceedings{deLimaLuizKurlekarGeorges2025, author = {de Lima Luiz, Anderson and Kurlekar, Shubham Vijay and Georges, Munir}, title = {Scalable engine and the performance of different LLM models in a SLURM based HPC architecture}, booktitle = {Elektronische Sprachsignalverarbeitung 2025: Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, url = {https://www.essv.de/paper.php?id=1265}, pages = {297 -- 304}, year = {2025}, language = {en} } @inproceedings{LiuSrinivasaganGeorges2025, author = {Liu, Huiyu and Srinivasagan, Gokul and Georges, Munir}, title = {Real-time audio transcriber for language barrier-free classrooms}, booktitle = {Elektronische Sprachsignalverarbeitung 2025: Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, url = {https://www.essv.de/paper.php?id=1247}, pages = {146 -- 154}, year = {2025}, language = {en} } @inproceedings{BoddudeLimaLuizGeorges2025, author = {Boddu, Raviteja and de Lima Luiz, Anderson and Georges, Munir}, title = {Significance-based summarization for lecture recordings: a multi-modal perspective}, booktitle = {Elektronische Sprachsignalverarbeitung 2025: Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, url = {https://www.essv.de/paper.php?id=1240}, pages = {93 -- 100}, year = {2025}, language = {en} } @inproceedings{deLimaLuizBodduGeorges2025, author = {de Lima Luiz, Anderson and Boddu, Raviteja and Georges, Munir}, title = {Evaluating Snippet Significance: A Framework for Audio and Text-Based Dialogue Summarization}, booktitle = {ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, Conference Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-6874-1}, doi = {https://doi.org/10.1109/ICASSP49660.2025.10888790}, year = {2025}, language = {en} } @inproceedings{GeorgesHuangBocklet2020, author = {Georges, Munir and Huang, Jonathan and Bocklet, Tobias}, title = {Compact Speaker Embedding: lrx-vector}, booktitle = {Proceedings Interspeech 2020}, publisher = {ISCA}, address = {Grenoble}, doi = {https://doi.org/10.21437/Interspeech.2020-2106}, pages = {3236 -- 3240}, year = {2020}, language = {en} } @inproceedings{Georges2020, author = {Georges, Munir}, title = {DNN Optimization in Low-Power Speech Processing}, booktitle = {CSCS '20: ACM Computer Science in Cars Symposium - Extended Abstracts}, publisher = {ACM}, address = {New York}, year = {2020}, language = {en} } @inproceedings{GlockerGeorges2022, author = {Glocker, Kevin and Georges, Munir}, title = {Hierarchical Multi-Task Transformers for Crosslingual Low Resource Phoneme Recognition}, booktitle = {Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022)}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg}, isbn = {978-1-959429-36-4}, url = {https://aclanthology.org/2022.icnlsp-1.21}, pages = {187 -- 192}, year = {2022}, abstract = {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.}, language = {en} } @inproceedings{ChenDeisherGeorges2023, author = {Chen, Liu and Deisher, Michael and Georges, Munir}, title = {An End-to-End Neural Network for Image-to-Audio Transformation}, booktitle = {Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-7281-6327-7}, doi = {https://doi.org/10.1109/ICASSP49357.2023.10096121}, year = {2023}, language = {en} } @inproceedings{HerygersVerkhodanovaColeretal.2023, author = {Herygers, Aaricia and Verkhodanova, Vass and Coler, Matt and Scharenborg, Odette and Georges, Munir}, title = {Bias in Flemish Automatic Speech Recognition}, booktitle = {Elektronische Sprachsignalverarbeitung 2023: Tagungsband der 34. Konferenz M{\"u}nchen, 1.-3. M{\"a}rz 2023}, editor = {Draxler, Christoph}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-303-4}, url = {https://www.essv.de/paper.php?id=1186}, pages = {158 -- 165}, year = {2023}, language = {en} } @inproceedings{RanzenbergerBockletFreisingeretal.2023, author = {Ranzenberger, Thomas and Bocklet, Tobias and Freisinger, Steffen and Frischholz, Lia and Georges, Munir and Glocker, Kevin and Herygers, Aaricia and Peinl, Ren{\´e} and Riedhammer, Korbinian and Schneider, Fabian and Simic, Christopher and Zakaria, Khabbab}, title = {The Hochschul-Assistenz-System HAnS: An ML-Based Learning Experience Platform}, booktitle = {Elektronische Sprachsignalverarbeitung 2023: Tagungsband der 34. Konferenz M{\"u}nchen, 1.-3. M{\"a}rz 2023}, editor = {Draxler, Christoph}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-303-4}, url = {https://www.essv.de/paper.php?id=1188}, pages = {168 -- 169}, year = {2023}, language = {en} } @inproceedings{KendrickFrohnmaierGeorges2021, author = {Kendrick, Caroline and Frohnmaier, Mariano and Georges, Munir}, title = {Audio-Visual Recipe Guidance for Smart Kitchen Devices}, booktitle = {ICNLSP 2021: Proceedings of the 4th International Conference on Natural Language and Speech Processing}, publisher = {ACL}, address = {Stroudsburg}, isbn = {978-1-955917-18-6}, doi = {https://aclanthology.org/2021.icnlsp-1.30}, pages = {257 -- 261}, year = {2021}, language = {en} } @inproceedings{GeorgesCzarnowskiBocklet2019, author = {Georges, Munir and Czarnowski, Krzysztof and Bocklet, Tobias}, title = {Ultra-Compact NLU: Neuronal Network Binarization as Regularization}, booktitle = {Proceedings Interspeech 2019}, publisher = {ISCA}, address = {Grenoble}, doi = {https://doi.org/10.21437/Interspeech.2019-2591}, pages = {809 -- 813}, year = {2019}, language = {en} } @inproceedings{StemmerGeorgesHoferetal.2017, author = {Stemmer, Georg and Georges, Munir and Hofer, Joachim and Rozen, Piotr and Bauer, Josef and Nowicki, Jakub and Bocklet, Tobias and Colett, Hannah R. and Falik, Ohad and Deisher, Michael and Downing, Sylvia J.}, title = {Speech Recognition and Understanding on Hardware-Accelerated DSP}, booktitle = {Interspeech 2017: Situated interaction}, publisher = {ISCA}, address = {Grenoble}, url = {https://www.isca-speech.org/archive/interspeech_2017/stemmer17_interspeech.html}, doi = {https://doi.org/10.21437/Interspeech.2017}, pages = {2036 -- 2037}, year = {2017}, language = {en} } @inproceedings{GeorgesKanthakKlakow2014, author = {Georges, Munir and Kanthak, Stephan and Klakow, Dietrich}, title = {Accurate client-server based speech recognition keeping personal data on the client}, booktitle = {2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-4799-2893-4}, issn = {2379-190X}, doi = {https://doi.org/10.1109/ICASSP.2014.6854205}, pages = {3271 -- 3275}, year = {2014}, language = {en} } @inproceedings{GeorgesKanthakKlakow2013, author = {Georges, Munir and Kanthak, Stephan and Klakow, Dietrich}, title = {Transducer-based speech recognition with dynamic language models}, booktitle = {Proceedings Interspeech 2013}, publisher = {ISCA}, address = {Grenoble}, doi = {doi.org/10.21437/Interspeech.2013-185}, pages = {642 -- 646}, year = {2013}, language = {en} } @inproceedings{GlockerHerygersGeorges2023, author = {Glocker, Kevin and Herygers, Aaricia and Georges, Munir}, title = {Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes}, booktitle = {INTERSPEECH 2023}, publisher = {ISCA}, address = {Grenoble}, doi = {https://doi.org/10.21437/Interspeech.2023-772}, pages = {2258 -- 2262}, year = {2023}, language = {en} } @inproceedings{FreisingerSchneiderHerygersetal.2023, author = {Freisinger, Steffen and Schneider, Fabian and Herygers, Aaricia and Georges, Munir and Bocklet, Tobias and Riedhammer, Korbinian}, title = {Unsupervised Multilingual Topic Segmentation of Video Lectures: What can Hierarchical Labels tell us about the Performance?}, booktitle = {Proceedings 9th Workshop on Speech and Language Technology in Education (SLaTE)}, publisher = {International Speech Communication Association (ISCA)}, address = {Baixas}, doi = {https://doi.org/10.21437/SLaTE.2023-27}, pages = {141 -- 145}, year = {2023}, language = {en} } @inproceedings{WuGeorges2024, author = {Wu, Di and Georges, Munir}, title = {A Pipeline for Automatic Construction and Applications of College Curriculum Knowledge Graph}, booktitle = {TSD 2024 Paper Abstracts}, url = {https://www.tsdconference.org/tsd2024/abstracts.html\#I1270}, year = {2024}, language = {en} } @inproceedings{HartungMallickGroettrupetal.2024, author = {Hartung, Kai and Mallick, Sambit and Gr{\"o}ttrup, S{\"o}ren and Georges, Munir}, title = {Evaluation Metrics in LLM Code Generation}, booktitle = {Text, Speech, and Dialogue: 27th International Conference, TSD 2024 Brno, Czech Republic, September 9-13, 2024 Proceedings, Part I}, editor = {N{\"o}th, Elmar and Hor{\´a}k, Aleš and Sojka, Petr}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-70563-2}, doi = {https://doi.org/10.1007/978-3-031-70563-2_17}, pages = {214 -- 226}, year = {2024}, language = {en} } @inproceedings{KumarGeorges2024, author = {Kumar, Ankit and Georges, Munir}, title = {Joint-Average Mean and Variance Feature Matching (JAMVFM) Semi-supervised GAN with Additional-Objective Training Function for Intent Detection}, booktitle = {Text, Speech, and Dialogue: 27th International Conference, TSD 2024 Brno, Czech Republic, September 9-13, 2024 Proceedings, Part II}, editor = {N{\"o}th, Elmar and Hor{\´a}k, Aleš and Sojka, Petr}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-70566-3}, doi = {https://doi.org/10.1007/978-3-031-70566-3_24}, pages = {275 -- 287}, year = {2024}, language = {en} }