Publications
2024
■ Anonymizing Speaker Voices: Easy to Imitate, Difficult to Recognize?
Jennifer Williams, Karla Pizzi, Natalia Tomashenko, Sneha Das
ICASSP 2024
[IEEE Xplore]
■ The VoicePrivacy 2024 Challenge Evaluation Plan
Natalia Tomashenko, Xiaoxiao Miao, Pierre Champion, Sarina Meyer, Xin Wang, Emmanuel Vincent, Michele Panariello, Nicholas Evans, Junichi Yamagishi, Massimiliano Todisco
2023
■ Federated learning for ASR based on wav2vec 2.0
Tuan Nguyen, Salima Mdhaffar, Natalia Tomashenko, Jean-François Bonastre, Yannick Estève
ICASSP 2023
[arxiv][IEEE Xplore]
■ Speaker anonymization using orthogonal Householder neural network
Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko
IEEE Transactions on Audio, Speech and Language Processing
[arxiv][IEEE Xplore ]
■ Evaluating the effects of task design on unfamiliar Francophone listener and automatic speaker identification performance
Benjamin O'Brien, Christine Meunier, Natalia Tomashenko, Alain Ghio, Jean-François Bonastre
Multimedia Tools and Applications Journal
■ LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Titouan Parcollet, Ha Nguyen, Solene Evain, Marcely Zanon Boito, Adrien Pupier, Salima Mdhaffar, Hang Le, Sina Alisamir, Natalia Tomashenko, Marco Dinarelli, Shucong Zhang, Alexandre Allauzen, Maximin Coavoux, Yannick Esteve, Mickael Rouvier, Jerome Goulian, Benjamin Lecouteux, Francois Portet, Solange Rossato, Fabien Ringeval, Didier Schwab, Laurent Besacier
Computer Speech and Language (journal, published in 2024)
[Computer Speech & Language] [arxiv]
■ Metrics for anonymization of unstructured datasets
Lydia Belkadi, Martine De Cock, Natasha Fernandes, Katherine Lee, Christina Lohr, Olga Ohrimenko, Andreas Nautsch, Laurens Sion, Natalia Tomashenko, Marc Tommasi, Peggy Valcke, Emmanuel Vincent
Report from Dagstuhl Seminar 21052: Privacy in Speech and Language Technology
[report]
2022
■ Privacy attacks for automatic speech recognition acoustic models in a federated learning framework
Natalia Tomashenko, Salima Mdhaffar, Marc Tommasi, Yannick Estève, Jean-François Bonastre
ICASSP 2022
[arxiv][poster][IEEE Xplore]
■ Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition
Salima Mdhaffar, Jean-François Bonastre, Marc Tommasi, Natalia Tomashenko, Yannick Estève
ICASSP 2022
[arxiv]
■ The VoicePrivacy 2022 Challenge evaluation plan
Natalia Tomashenko, Xin Wang, Xiaoxiao Miao, Hubert Nourtel, Pierre Champion, Massimiliano Todisco, Emmanuel Vincent, Nicholas Evans, Junichi Yamagishi, Jean-François Bonastre
[arxiv]
■ Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models
Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko
[arxiv]
■ Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditions
Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko
Interspeech 2022
[arxiv]
■ A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems
Marcely Zanon Boito, Laurent Besacier, Natalia Tomashenko, Yannick Estève
Interspeech 2022
[arxiv]
■ Multi-lingual Speech to Speech Translation for Under-Resourced Languages
Anthony Larcher, Yannick Estève, Mickael Rouvier, Natalia Tomashenko, Jarod Duret, et al.
ESPERANTO/JSALT workshop report
[hal]
■ Sur la vérification du locuteur à partir de traces d’exécution de modèles acoustiques personnalisés
Natalia Tomashenko, Salima Mdhaffar, Marc Tommasi, Yannick Estève, Jean-François Bonastre
Journées d'Études sur la Parole - JEP2022
[hal]
■ Extraction d'informations liées au locuteur depuis un modèle acoustique personnalisé
Salima Mdhaffar, Jean-François Bonastre, Marc Tommasi, Natalia Tomashenko, Yannick Estève
Journées d'Études sur la Parole - JEP2022
■ Modèles neuronaux pré-appris par auto-supervision sur des enregistrements de parole en français
Solène Evain, Ha Nguyen, Hang Le, Marcely Zanon Boito, Salima Mdhaffar, Sina Alisamir, Ziyi Tong, Natalia Tomashenko, Marco Dinarelli, Titouan Parcollet, Alexandre Allauzen, Yannick Estève, Benjamin Lecouteux, François Portet, Solange Rossato, Fabien Ringeval, Didier Schwab and Laurent Besacier
Journées d'Études sur la Parole - JEP2022
■ LeBenchmark, un référentiel d'évaluation pour le français oral
Hang Le, Sina Alisamir, Marco Dinarelli, Fabien Ringeval, Solène Evain, Ha Nguyen, Marcely Zanon Boito, Salima Mdhaffar, Ziyi Tong, Natalia Tomashenko, Titouan Parcollet, Allauzen Alexandre, Yannick Estève, Benjamin Lecouteux, François Portet, Solange Rossato, Didier Schwab and Laurent Besacier
Journées d'Études sur la Parole - JEP2022
2021
■ The VoicePrivacy 2020 Challenge: Results and findings
Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Jose Patino, Brij Mohan Lal Srivastava, Paul-Gauthier Noé, Andreas Nautsch, Nicholas Evans, Junichi Yamagishi, Benjamin O'Brien, Anaïs Chanclu, Jean-François Bonastre, Massimiliano Todisco, Mohamed Maouche.
Computer Speech and Language (journal, published in 2022)
[Computer Speech & Language ][arxiv]
■ Supplementary material to the paper: The VoicePrivacy 2020 Challenge: Results and findings
Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Jose Patino, Brij Mohan Lal Srivastava, Paul-Gauthier Noé, Andreas Nautsch, Nicholas Evans, Junichi Yamagishi, Benjamin O'Brien, Anaïs Chanclu, Jean-François Bonastre, Massimiliano Todisco, Mohamed Maouche.
Report
[pdf]
■ Anonymous speaker clusters: Making distinctions between anonymised speech recordings with clustering interface
Benjamin O'Brien, Natalia Tomashenko, Anaïs Chanclu, Jean-François Bonastre
Interspeech 2021
■ Towards a unified assessment framework of speech pseudonymisation
Paul-Gauthier Noé, Andreas Nautsch, Nicholas Evans, Jose Patino, Jean-François Bonastre, Natalia Tomashenko, Driss Matrouf
Computer Speech & Language
[CSL]
■ Benchmarking and challenges in security and privacy for voice biometrics
Jean-Francois Bonastre, Hector Delgado, Nicholas Evans, Tomi Kinnunen, Kong Aik Lee, Xuechen Liu, Andreas Nautsch, Paul-Gauthier Noe, Jose Patino, Md Sahidullah, Brij Mohan Lal Srivastava, Massimiliano Todisco, Natalia Tomashenko, Emmanuel Vincent, Xin Wang, Junichi Yamagishi
ISCA Symposium on Security and Privacy in Speech Communication
■ LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
Solene Evain, Ha Nguyen, Hang Le, Marcely Zanon Boito, Salima Mdhaffar, Sina Alisamir, Ziyi Tong, Natalia Tomashenko, Marco Dinarelli, Titouan Parcollet, Alexandre Allauzen, Yannick Esteve, Benjamin Lecouteux, Francois Portet, Solange Rossato, Fabien Ringeval, Didier Schwab, Laurent Besacier
Interspeech 2021
■ Task Agnostic and Task Specific Self-Supervised Learning from Speech with LeBenchmark
Solene Evain, Ha Nguyen, Hang Le, Marcely Zanon Boito, Salima Mdhaffar, Sina Alisamir, Ziyi Tong, Natalia Tomashenko, Marco Dinarelli, Titouan Parcollet, Alexandre Allauzen, Yannick Esteve, Benjamin Lecouteux, Francois Portet, Solange Rossato, Fabien Ringeval, Didier Schwab, Laurent Besacier
NeurIPS Thirty-fifth Annual Conference on Neural Information Processing Systems 2021: Datasets and Benchmarks Track
[paper] [poster]
■ Speaker anonymisation using the McAdams coefficient
Jose Patino, Natalia Tomashenko, Massimiliano Todisco, Andreas Nautsch, Nicholas Evans.
Interspeech 2021
[ISCA archive] [arxiv]
■ Privacy and utility of x-vector based speaker anonymization
Brij M. L. Srivastava, Mohamed Maouche, Md Sahidullah, Emmanuel Vincent, Aurélien Bellet, Marc Tommasi, Natalia Tomashenko, Xin Wang, Junichi Yamagishi.
IEEE/ACM Transactions on Audio, Speech, and Language Processing
■ ON-TRAC’ systems for the IWSLT 2021 low-resource speech translation and multilingual speech translation shared tasks
Le, H., Barbier, F., Nguyen, H., Tomashenko, N., Mdhaffar, S., Gahbiche, S., Fethi, B., Lecouteux, B., Schwab, D. and Estève, Y.
International Conference on Spoken Language Translation (IWSLT)
[paper]
2020
■ Introducing the VoicePrivacy initiative
Natalia Tomashenko, Brij Mohan Lal Srivastava, Xin Wang, Emmanuel Vincent, Andreas Nautsch, Junichi Yamagishi, Nicholas Evans, Jose Patino, Jean-François Bonastre, Paul-Gauthier Noé, Massimiliano Todisco.
Interspeech 2020
[arxiv] [slides] [ISCA archive] [video] [code]
■ Design choices for x-vector based speaker anonymization
Brij Mohan Lal Srivastava, Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Junichi Yamagishi, Mohamed Maouche, Aurélien Bellet, Marc Tommasi.
Interspeech 2020
[arxiv] [slides] [ISCA archive] [video] [code]
■ The Privacy ZEBRA: Zero Evidence Biometric Recognition Assessment
Andreas Nautsch, Jose Patino, Natalia Tomashenko, Junichi Yamagishi, Paul-Gauthier Noe, Jean-Francois Bonastre, Massimiliano Todisco, Nicholas Evans.
Interspeech 2020
[arxiv] [slides] [ISCA archive] [video] [code]
■ Speech Pseudonymisation Assessment Using Voice Similarity Matrices
Paul-Gauthier Noé, Jean-François Bonastre, Driss Matrouf, Natalia Tomashenko, Andreas Nautsch, Nicholas Evans.
Interspeech 2020
[arxiv] [slides] [ISCA archive] [video] [code]
■ Investigating Self-supervised Pre-training for End-to-end Speech Translation
Ha Nguyen, Fethi Bougares, Natalia Tomashenko, Yannick Estève, Laurent Besacier.
Interspeech 2020
[arxiv] [slides] [ISCA archive] [video]
■ Dialogue history integration into end-to-end signal-to-concept spoken language understanding systems
Natalia Tomashenko, Christian Raymond, Antoine Caubrière, Renato De Mori, Yannick Estève.
ICASSP 2020
[arxiv] [slides] [IEEE Xplore] [video]
■ Error Analysis Applied to End-to-End Spoken Language Understanding
Antoine Caubrière, Sahar Ghannay, Natalia Tomashenko, Renato De Mori, Antoine Laurent, Emmanuel Morin, Yannick Estève.
ICASSP 2020
[pdf] [slides] [IEEE Xplore] [video]
■ ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020
Maha Elbayad, Ha Nguyen, Fethi Bougares, Natalia Tomashenko, Antoine Caubrière, Benjamin Lecouteux, Yannick Estève, Laurent Besacier.
IWSLT 2020 (ACL)
■ Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models
Natalia Tomashenko, Yuri Khokhlov, Yannick Estève.
preprint
[arxiv]
■ The VoicePrivacy 2020 Challenge Evaluation Plan
Natalia Tomashenko, Brij Mohan Lal Srivastava, Xin Wang, Emmanuel Vincent, Andreas Nautsch, Junichi Yamagishi, Nicholas Evans, Jean-François Bonastre, Paul-Gauthier Noé, Massimiliano Todisco, Jose Patino.
[pdf]
2019
■ Investigating adaptation and transfer learning for end-to-end spoken language understanding from speech
Natalia Tomashenko, Antoine Caubrière, Yannick Estève.
Interspeech 2019
[arxiv] [ISCA archive] [poster] [video]
■ Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability
Antoine Caubrière, Natalia Tomashenko, Antoine Laurent, Emmanuel Morin, Nathalie Camelin, Yannick Estève.
Interspeech 2019
[arxiv] [ISCA archive] [poster] [video]
■ Recent advances in end-to-end spoken language understanding
Natalia Tomashenko, Antoine Caubrière, Yannick Estève, Antoine Laurent, Emmanuel Morin.
International Conference on Statistical Language and Speech Processing (SLSP) 2019
[arxiv] [Springer link] [slides]
■ ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task
Ha Nguyen, Natalia Tomashenko, Marcely Zanon Boito, Antoine Caubrière, Fethi Bougares, Mickael Rouvier, Laurent Besacier, Yannick Estève.
IWSLT 2019
[arxiv] [slides]
■ Curriculum d'apprentissage: reconnaissance d'entités nommées pour l'extraction de concepts sémantiques
Antoine Caubrière, Natalia Tomashenko, Yannick Estève, Antoine Laurent, Emmanuel Morin.
TALN 2019
[pdf]
2018
■ Speaker Adaptive Training and Mixup Regularization for Neural Network Acoustic Models in Automatic Speech Recognition
Natalia Tomashenko, Yuri Khokhlov, Yannick Estève.
Interspeech 2018
[ISCA archive] [poster] [code]
■ An Investigation of Mixup Training Strategies for Acoustic Models in ASR
Ivan Medennikov, Yuri Y Khokhlov, Aleksei Romanenko, Dmitry Popov, Natalia Tomashenko, Ivan Sorokin, Alexander Zatvornitskiy.
Interspeech 2018
[ISCA archive] [poster] [code]
■ Evaluation of feature-space speaker adaptation for end-to-end acoustic models
Natalia Tomashenko, Yannick Estève.
International Conference on Language Resources and Evaluation (LREC) 2018
[pdf] [poster]
■ TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation
François Hernandez, Vincent Nguyen, Sahar Ghannay, Natalia Tomashenko, Yannick Estève.
International Conference on Speech and Computer (SPECOM) 2018
[arxiv] [Springer link]
■ Impact des techniques d’adaptation au locuteur dans l’espace des paramètres pour des modèles acoustiques purement neuronaux
Natalia Tomashenko, Yannick Estève.
IXXXIIe Journées d’Études sur la Parole (JEP) 2018
[pdf] [poster]
2017
■ Speaker adaptation of deep neural network acoustic models using Gaussian mixture model framework in automatic speech recognition systems
Natalia Tomashenko.
PhD thesis
[pdf] [slides]
■ Fast and accurate OOV decoder on high-level features
Yuri Khokhlov, Natalia Tomashenko, Ivan Medennikov, Alexei Romanenko
Interspeech 2017
[pdf] [poster]
■ The STC Keyword Search System for OpenKWS 2016 Evaluation
Yuri Y Khokhlov, Ivan Medennikov, Aleksei Romanenko, Valentin Mendelev, Maxim Korenevsky, Alexey Prudnikov, Natalia Tomashenko, Alexander Zatvornitsky
Interspeech 2017
[pdf]
■ Acoustic modeling in the STC keyword search system for OpenKWS 2016 evaluation
Ivan Medennikov, Aleksei Romanenko, Alexey Prudnikov, Valentin Mendelev, Yuri Khokhlov, Maxim Korenevsky, Natalia Tomashenko, Alexander Zatvornitskiy
International Conference on Speech and Computer (SPECOM) 2017
[pdf] [Springer link]
2016
■ LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic challenge
Natalia Tomashenko, Kévin Vythelingum, Anthony Rousseau, Yannick Estève
2016 IEEE Spoken Language Technology Workshop (SLT)
[pdf] [IEEE Xplore]
■ On the Use of Gaussian Mixture Model Framework to Improve Speaker Adaptation of Deep Neural Network Acoustic Models
Natalia Tomashenko, Yuri Khokhlov, Yannick Estève
Interspeech 2016
[ISCA archive] [poster]
■ A new perspective on combining GMM and DNN frameworks for speaker adaptation
Natalia Tomashenko, Yuri Khokhlov, Yannick Estève
International Conference on Statistical Language and Speech Processing (SLSP) 2016
[Springer link] [slides]
■ Exploring GMM-derived features for unsupervised adaptation of deep neural network acoustic models
Natalia Tomashenko, Yuri Khokhlov, Anthony Larcher, Yannick Estève
International Conference on Speech and Computer (SPECOM) 2016
[pdf] [Springer link]
■ Exploration de paramètres acoustiques dérivés de GMMs pour l'adaptation non supervisée de modèles acoustiques à base de réseaux de neurones profonds
Natalia Tomashenko, Yuri Khokhlov, Anthony Larcher, Yannick Estève
Journées d’Études sur la Parole (JEP'16)
[pdf]
2015
■ GMM-derived features for effective unsupervised adaptation of deep neural network acoustic models
Natalia Tomashenko, Yuri Khokhlov
Interspeech 2015
■ A bilingual Kazakh-Russian system for automatic speech recognition and synthesis
Olga Khomitsevich, Valentin Mendelev, Natalia Tomashenko, Sergey Rybin, Ivan Medennikov, Saule Kudubayeva
International Conference on Speech and Computer (SPECOM) 2015
[pdf][Springer link]
■ Speaker verification using spectral and durational segmental characteristics
Elena Bulgakova, Aleksei Sholohov, Natalia Tomashenko, Yuri Matveev
International Conference on Speech and Computer (SPECOM) 2015
[pdf][Springer link]
2014
■ Speaker adaptation of context dependent deep neural networks based on MAP-adaptation and GMM-derived feature processing
Natalia Tomashenko, Yuri Khokhlov
Interspeech 2014
■ Speaking rate estimation based on deep neural networks
Natalia Tomashenko, Yuri Khokhlov
International Conference on Speech and Computer (SPECOM) 2014
■ Automated closed captioning for Russian live broadcasting
Kirill Levin, Irina Ponomareva, Anna Bulusheva, G Chernykh, Ivan Medennikov, Nickolay Merkin, Alexey Prudnikov, Natalia Tomashenko
Interspeech 2014
■ State level control for acoustic model training
German Chernykh, Maxim Korenevsky, Kirill Levin, Irina Ponomareva, Natalia Tomashenko
International Conference on Speech and Computer (SPECOM) 2014
[pdf][Springer link]