Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering.

Iuliia Nigmatulina Pradeep Rangappa Juan Zuluaga-Gomez Srikanth R. Madikeri Andrés Carofilis Jeena J. Prakash Sergio Burdisso Shashi Kumar Esaú Villatoro-Tello Iuliia Nigmatulina Petr Motlícek Karthik Pandia Aravind Ganapathiraju Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering. 1-5 2025 ICASSP https://doi.org/10.1109/ICASSP49660.2025.10888138 conf/icassp/2025 db/conf/icassp/icassp2025.html#RangappaZMCPBKV25

Juan Pablo Zuluaga Gomez Karel Veselý Igor Szöke Alexander Blatt Petr Motlícek Martin Kocour Khalid Choukri Iuliia Nigmatulina Claudia Cevenini Allan Tart Jan Cernocký Dietrich Klakow ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications. 2024 (5):1-45 2 J. Data-centric Mach. Learn. Res. https://data.mlr.press/assets/pdf/v02-5.pdf db/journals/dmlr/dmlr2.html#GomezVSBMKCNCTCK24 streams/journals/dmlr

Shashi Kumar Srikanth R. Madikeri Iuliia Nigmatulina Esaú Villatoro-Tello Petr Motlícek Karthik Pandia S. Pavankumar Dubagunta Aravind Ganapathiraju Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers. 12592-12596 2024 ICASSP https://doi.org/10.1109/ICASSP48485.2024.10446130 conf/icassp/2024 db/conf/icassp/icassp2024.html#KumarMNVMPDG24 Esaú Villatoro-Tello Srikanth R. Madikeri Bidisha Sharma Driss Khalil Shashi Kumar Iuliia Nigmatulina Petr Motlícek Aravind Ganapathiraju Probability-Aware Word-Confusion-Network-To-Text Alignment Approach for Intent Classification. 12617-12621 2024 ICASSP https://doi.org/10.1109/ICASSP48485.2024.10445934 conf/icassp/2024 db/conf/icassp/icassp2024.html#Villatoro-Tello24 Mrinmoy Bhattacharjee Iuliia Nigmatulina Amrutha Prasad Pradeep Rangappa Srikanth R. Madikeri Petr Motlícek Hartmut Helmke Matthias Kleinert Contextual Biasing Methods for Improving Rare Word Detection in Automatic Speech Recognition. 12652-12656 2024 ICASSP https://doi.org/10.1109/ICASSP48485.2024.10447465 conf/icassp/2024 db/conf/icassp/icassp2024.html#BhattacharjeeNP24

Shashi Kumar Srikanth R. Madikeri Juan Zuluaga-Gomez Iuliia Nigmatulina Esaú Villatoro-Tello Sergio Burdisso Petr Motlícek Karthik Pandia Aravind Ganapathiraju TokenVerse: Unifying Speech and NLP Tasks via Transducer-based ASR. 2024 abs/2407.04444 CoRR https://doi.org/10.48550/arXiv.2407.04444 db/journals/corr/corr2407.html#abs-2407-04444 streams/journals/corr

Esaú Villatoro-Tello Srikanth R. Madikeri Juan Zuluaga-Gomez Bidisha Sharma Seyyed Saeed Sarfjoo Iuliia Nigmatulina Petr Motlícek Alexei V. Ivanov Aravind Ganapathiraju Effectiveness of Text, Acoustic, and Lattice-Based Representations in Spoken Language Understanding Tasks. 1-5 2023 ICASSP https://doi.org/10.1109/ICASSP49357.2023.10095168 conf/icassp/2023 db/conf/icassp/icassp2023.html#VillatoroTelloMZSSNMIG23 Iuliia Nigmatulina Srikanth R. Madikeri Esaú Villatoro-Tello Petr Motlícek Juan Zuluaga-Gomez Karthik Pandia Aravind Ganapathiraju Implementing Contextual Biasing in GPU Decoder for Online ASR. 4494-4498 2023 INTERSPEECH https://doi.org/10.21437/Interspeech.2023-2449 conf/interspeech/2023 db/conf/interspeech/interspeech2023.html#NigmatulinaMVMZ23

Juan Zuluaga-Gomez Amrutha Prasad Iuliia Nigmatulina Petr Motlícek Matthias Kleinert A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers. 2023 abs/2304.07842 CoRR https://doi.org/10.48550/arXiv.2304.07842 db/journals/corr/corr2304.html#abs-2304-07842

Juan Zuluaga-Gomez Iuliia Nigmatulina Amrutha Prasad Petr Motlícek Driss Khalil Srikanth R. Madikeri Allan Tart Igor Szöke Vincent Lenders Mickaël Rigault Khalid Choukri Lessons Learned in ATCO2: 5000 hours of Air Traffic Control Communications for Robust Automatic Speech Recognition and Understanding. 2023 abs/2305.01155 CoRR https://doi.org/10.48550/arXiv.2305.01155 db/journals/corr/corr2305.html#abs-2305-01155

Iuliia Nigmatulina Srikanth R. Madikeri Esaú Villatoro-Tello Petr Motlícek Juan Zuluaga-Gomez Karthik Pandia Aravind Ganapathiraju Implementing contextual biasing in GPU decoder for online ASR. 2023 abs/2306.15685 CoRR https://doi.org/10.48550/arXiv.2306.15685 db/journals/corr/corr2306.html#abs-2306-15685

Iuliia Nigmatulina Juan Zuluaga-Gomez Amrutha Prasad Seyyed Saeed Sarfjoo Petr Motlícek A Two-Step Approach to Leverage Contextual Data: Speech Recognition in Air-Traffic Communications. 6282-6286 2022 ICASSP https://doi.org/10.1109/ICASSP43922.2022.9746563 conf/icassp/2022 db/conf/icassp/icassp2022.html#NigmatulinaZPSM22 Juan Zuluaga-Gomez Amrutha Prasad Iuliia Nigmatulina Seyyed Saeed Sarfjoo Petr Motlícek Matthias Kleinert Hartmut Helmke Oliver Ohneiser Qingran Zhan How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted Asr? an Extensive Benchmark on Air Traffic Control Communications. 205-212 2022 SLT https://doi.org/10.1109/SLT54892.2023.10022724 conf/slt/2022 db/conf/slt/slt2022.html#ZuluagaGomezPNSMKHOZ22 Juan Zuluaga-Gomez Seyyed Saeed Sarfjoo Amrutha Prasad Iuliia Nigmatulina Petr Motlícek Karel Ondrej Oliver Ohneiser Hartmut Helmke Bertraffic: Bert-Based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications. 633-640 2022 SLT https://doi.org/10.1109/SLT54892.2023.10022718 conf/slt/2022 db/conf/slt/slt2022.html#ZuluagaGomezSPNMOOH22

Iuliia Nigmatulina Juan Zuluaga-Gomez Amrutha Prasad Seyyed Saeed Sarfjoo Petr Motlícek A two-step approach to leverage contextual data: speech recognition in air-traffic communications. 2022 abs/2202.03725 CoRR https://arxiv.org/abs/2202.03725 db/journals/corr/corr2202.html#abs-2202-03725

Juan Zuluaga-Gomez Amrutha Prasad Iuliia Nigmatulina Seyyed Saeed Sarfjoo Petr Motlícek Matthias Kleinert Hartmut Helmke Oliver Ohneiser Qingran Zhan How Does Pre-trained Wav2Vec2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications. 2022 abs/2203.16822 CoRR https://doi.org/10.48550/arXiv.2203.16822 db/journals/corr/corr2203.html#abs-2203-16822

Juan Zuluaga-Gomez Karel Veselý Igor Szöke Petr Motlícek Martin Kocour Mickaël Rigault Khalid Choukri Amrutha Prasad Seyyed Saeed Sarfjoo Iuliia Nigmatulina Claudia Cevenini Pavel Kolcárek Allan Tart Jan Cernocký ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications. 2022 abs/2211.04054 CoRR https://doi.org/10.48550/arXiv.2211.04054 db/journals/corr/corr2211.html#abs-2211-04054

Amrutha Prasad Juan Zuluaga-Gomez Petr Motlícek Seyyed Saeed Sarfjoo Iuliia Nigmatulina Karel Veselý Speech and Natural Language Processing Technologies for Pseudo-Pilot Simulator. 2022 abs/2212.07164 CoRR https://doi.org/10.48550/arXiv.2212.07164 db/journals/corr/corr2212.html#abs-2212-07164

Juan Zuluaga-Gomez Iuliia Nigmatulina Amrutha Prasad Petr Motlícek Karel Veselý Martin Kocour Igor Szöke Contextual Semi-Supervised Learning: An Approach to Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems. 3296-3300 2021 Interspeech https://doi.org/10.21437/Interspeech.2021-1373 conf/interspeech/2021 db/conf/interspeech/interspeech2021.html#Zuluaga-GomezNP21

Juan Zuluaga-Gomez Iuliia Nigmatulina Amrutha Prasad Petr Motlícek Karel Veselý Martin Kocour Igor Szöke Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems. 2021 abs/2104.03643 CoRR https://arxiv.org/abs/2104.03643 db/journals/corr/corr2104.html#abs-2104-03643

Iuliia Nigmatulina Rudolf A. Braun Juan Zuluaga-Gomez Petr Motlícek Improving callsign recognition with air-surveillance data in air-traffic communication. 2021 abs/2108.12156 CoRR https://arxiv.org/abs/2108.12156 db/journals/corr/corr2108.html#abs-2108-12156

Amrutha Prasad Juan Zuluaga-Gomez Petr Motlícek Oliver Ohneiser Hartmut Helmke Seyyed Saeed Sarfjoo Iuliia Nigmatulina Grammar Based Identification Of Speaker Role For Improving ATCO And Pilot ASR. 2021 abs/2108.12175 CoRR https://arxiv.org/abs/2108.12175 db/journals/corr/corr2108.html#abs-2108-12175

Juan Zuluaga-Gomez Seyyed Saeed Sarfjoo Amrutha Prasad Iuliia Nigmatulina Petr Motlícek Oliver Ohneiser Hartmut Helmke BERTraffic: A Robust BERT-Based Approach for Speaker Change Detection and Role Identification of Air-Traffic Communications. 2021 abs/2110.05781 CoRR https://arxiv.org/abs/2110.05781 db/journals/corr/corr2110.html#abs-2110-05781

Tannon Kew Iuliia Nigmatulina Lorenz Nagele Tanja Samardzic UZH TILT: A Kaldi recipe for Swiss German Speech to Standard German Text. 2020 SwissText/KONVENS https://ceur-ws.org/Vol-2624/germeval-task4-paper4.pdf conf/swisstext/2020 db/conf/swisstext/swisstext2020.html#KewNNS20 Iuliia Nigmatulina Tannon Kew Tanja Samardzic ASR for Non-standardised Languages with Dialectal Variation: the case of Swiss German. 15-24 2020 VarDial@COLING https://aclanthology.org/2020.vardial-1.2/ conf/vardial/2020 db/conf/vardial/vardial2020.html#NigmatulinaKS20 Mrinmoy Bhattacharjee Alexander Blatt Rudolf A. Braun Sergio Burdisso Roberto Andrés Vasco CarofilisAndrés Carofilis Jan Cernocký Claudia Cevenini Khalid Choukri S. Pavankumar Dubagunta Aravind Ganapathiraju Juan Pablo Zuluaga Gomez Hartmut Helmke Alexei V. Ivanov Tannon Kew Driss Khalil Dietrich Klakow Matthias Kleinert Martin Kocour Pavel Kolcárek Shashi Kumar Vincent Lenders Srikanth R. Madikeri Petr Motlícek Lorenz Nagele Oliver Ohneiser Karel Ondrej D. S. Karthik PandiaKarthik Pandia Jeena J. Prakash Amrutha Prasad Pradeep Rangappa Mickaël Rigault Tanja Samardzic Seyyed Saeed Sarfjoo Bidisha Sharma Igor Szöke Allan Tart Karel Veselý Esaú Villatoro-Tello Qingran Zhan Juan Zuluaga-Gomez