Natalia Tomashenko
32
Documents
Publications
|
Privacy and utility of x-vector based speaker anonymizationIEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, ⟨10.1109/TASLP.2022.3190741⟩
Article dans une revue
hal-03197376v3
|
|
The VoicePrivacy 2020 Challenge: Results and findingsComputer Speech and Language, 2022, 74, pp.101362. ⟨10.1016/j.csl.2022.101362⟩
Article dans une revue
hal-03332224v4
|
|
Extraction d'informations liées au locuteur depuis un modèle acoustique personnaliséJEP 2022, Jun 2022, île de Noirmoutier, France
Communication dans un congrès
hal-03706944v1
|
|
On speaker verification from the neural network footprint of personalized acoustic modelsJournées d'Études sur la Parole - JEP2022, Jun 2022, Île de Noirmoutier, France
Communication dans un congrès
hal-03626964v1
|
|
ON-TRAC' systems for the IWSLT 2021 low-resource speech translation and multilingual speech translation shared tasksInternational Conference on Spoken Language Translation (IWSLT), Aug 2021, Bangkok (virtual), Thailand. ⟨10.18653/v1/2021.iwslt-1.20⟩
Communication dans un congrès
hal-03298854v2
|
|
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from SpeechINTERSPEECH 2021: Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic
Communication dans un congrès
hal-03317730v3
|
Error analysis applied to end-to end spoken language understanding45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020), May 2020, Barcelona, Spain. pp.8514-8518, ⟨10.1109/ICASSP40776.2020.9054455⟩
Communication dans un congrès
hal-02465899v1
|
|
|
Introducing the VoicePrivacy initiativeINTERSPEECH 2020, Oct 2020, Shanghai, China
Communication dans un congrès
hal-02562199v3
|
Dialogue History Integration into End-to-End Signal-to-Concept Spoken Language Understanding SystemsICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2020, Barcelona, Spain. pp.5, ⟨10.1109/ICASSP40776.2020.9053247⟩
Communication dans un congrès
hal-02551760v1
|
|
|
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020Proceedings of the 17th International Conference on Spoken Language Translation, Jul 2020, Seattle, WA, United States. pp.35-43, ⟨10.18653/v1/2020.iwslt-1.2⟩
Communication dans un congrès
hal-02895893v1
|
|
Speech Pseudonymisation Assessment Using Voice Similarity MatricesInterspeech 2020, Oct 2020, Shanghai, China
Communication dans un congrès
hal-02925559v1
|
|
Design Choices for X-vector Based Speaker AnonymizationINTERSPEECH 2020, International Speech Communication Association (ISCA), Oct 2020, Shanghai, China
Communication dans un congrès
hal-02610447v2
|
|
Investigating Self-supervised Pre-training for End-to-end Speech TranslationInterspeech 2020, Oct 2020, Shangai (Virtual Conf), China
Communication dans un congrès
hal-02962186v1
|
|
ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task16th International Workshop on Spoken Language Translation 2019, Nov 2019, Hong Kong, China
Communication dans un congrès
hal-02352949v1
|
|
Recent Advances in End-to-End Spoken Language Understanding7th International Conference on Statistical Language and Speech Processing (SLSP), Oct 2019, Ljubljana, Slovenia
Communication dans un congrès
hal-02353011v1
|
|
Investigating Adaptation and Transfer Learning for End-to-End Spoken Language Understanding from SpeechInterspeech 2019, Sep 2019, Graz, Austria. pp.824-828, ⟨10.21437/Interspeech.2019-2158⟩
Communication dans un congrès
hal-02307811v1
|
|
Curriculum d'apprentissage : reconnaissance d'entités nommées pour l'extraction de concepts sémantiques26e conférence sur le Traitement Automatique des Langues Naturelles (TALN), Jul 2019, Toulouse, France
Communication dans un congrès
hal-02304614v1
|
|
Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability20th Annual Conference of the International Speech Communication Association (InterSpeech), Sep 2019, Graz, Austria. pp.1198-1202, ⟨10.21437/interspeech.2019-1832⟩
Communication dans un congrès
hal-02304597v1
|
|
Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic ModelsLREC 2018, May 2018, Miyazaki, Japan
Communication dans un congrès
hal-01728526v1
|
Impact des techniques d'adaptation au locuteur dans l'espace des paramètres pour des modèles acoustiques purement neuronauxXXXIIe Journées d'Etudes sur la Parole, Jun 2018, Aix-en-Provence, France
Communication dans un congrès
hal-01757772v1
|
|
Speaker Adaptive Training and Mixup Regularization for Neural Network Acoustic Models in Automatic Speech RecognitionInterspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2209⟩
Communication dans un congrès
hal-01870865v1
|
|
An Investigation of Mixup Training Strategies for Acoustic Models in ASRInterspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2191⟩
Communication dans un congrès
hal-01876337v1
|
|
Fast and Accurate OOV Decoder on High-Level FeaturesINTERSPEECH 2017, Aug 2017, Stockholm, Sweden. pp.2884-2888, ⟨10.21437/Interspeech.2017-1367⟩
Communication dans un congrès
hal-01681375v1
|
|
|
Exploring GMM-derived Features for Unsupervised Adaptation of Deep Neural Network Acoustic Models18th International Conference on Speech and Computer, 2016, Budapest, Hungary
Communication dans un congrès
hal-01433184v1
|
|
Exploration de paramètres acoustiques dérivés de GMMs pour l'adaptation non supervisée de modèles acoustiques à base de réseaux de neurones profondsJournées d’Études sur la Parole (JEP'16), 2016, Paris, France
Communication dans un congrès
hal-01456899v1
|
On the Use of Gaussian Mixture Model Framework to Improve Speaker Adaptation of Deep Neural Network Acoustic ModelsInterspeech 2016, 2016, San Francisco (CA, USA), Unknown Region
Communication dans un congrès
hal-01433178v1
|
|
A New Perspective on Combining GMM and DNN Frameworks for Speaker Adaptation4th International Conference on Statistical Language and Speech Processing - SLSP 2016, 2016, Pilsen, Czech Republic
Communication dans un congrès
hal-01433182v1
|
|
LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic ChallengeIEEE Workshop on Spoken Language Technology, Dec 2016, San Diego, CA, USA, United States. ⟨10.1109/SLT.2016.7846278⟩
Communication dans un congrès
hal-01433188v1
|
|
The VoicePrivacy 2022 Challenge Evaluation Plan2022
Pré-publication, Document de travail
hal-03623516v2
|
|
Supplementary material to the paper The VoicePrivacy 2020 Challenge: Results and findings2022
Pré-publication, Document de travail
hal-03335126v6
|
|
Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models2020
Pré-publication, Document de travail
hal-02551714v1
|
|
The VoicePrivacy 2020 Challenge Evaluation Plan[0] LIA - Laboratoire Informatique d'Avignon; MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery; Eurecom [Sophia Antipolis]; University of Edinburgh. 2020
Rapport
hal-03623450v2
|