@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} }