Natalia Tomashenko
Natalia Tomashenko
Adresse e-mail validée de univ-avignon.fr
Titre
Citée par
Citée par
Année
TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation
F Hernandez, V Nguyen, S Ghannay, N Tomashenko, Y Estève
International Conference on Speech and Computer, 198-208, 2018
482018
Speaker adaptation of context dependent deep neural networks based on MAP-adaptation and GMM-derived feature processing
N Tomashenko, Y Khokhlov
Fifteenth Annual Conference of the International Speech Communication …, 2014
402014
GMM-derived features for effective unsupervised adaptation of deep neural network acoustic models
N Tomashenko, Y Khokhlov
Sixteenth Annual Conference of the International Speech Communication …, 2015
182015
Automated closed captioning for Russian live broadcasting
K Levin, I Ponomareva, A Bulusheva, G Chernykh, I Medennikov, ...
Fifteenth Annual Conference of the International Speech Communication …, 2014
182014
On the Use of Gaussian Mixture Model Framework to Improve Speaker Adaptation of Deep Neural Network Acoustic Models.
NA Tomashenko, YY Khokhlov, Y Estève
INTERSPEECH, 3788-3792, 2016
162016
Speech recognition performance evaluation for LVCSR system
Y Khokhlov, N Tomashenko
Proc. 14th Int. Conf. on Speech and Computer (SPECOM 2011). Kazan', Russia …, 2011
152011
The STC Keyword Search System for OpenKWS 2016 Evaluation.
YY Khokhlov, I Medennikov, A Romanenko, V Mendelev, M Korenevsky, ...
INTERSPEECH, 3602-3606, 2017
142017
Fast algorithm for automatic alignment of speech and imperfect text data
NA Tomashenko, YY Khokhlov
International Conference on Speech and Computer, 146-153, 2013
142013
LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic challenge
N Tomashenko, K Vythelingum, A Rousseau, Y Estève
2016 IEEE Spoken Language Technology Workshop (SLT), 285-291, 2016
132016
A bilingual Kazakh-Russian system for automatic speech recognition and synthesis
O Khomitsevich, V Mendelev, N Tomashenko, S Rybin, I Medennikov, ...
International Conference on Speech and Computer, 25-33, 2015
122015
Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability
A Caubrière, N Tomashenko, A Laurent, E Morin, N Camelin, Y Estève
arXiv preprint arXiv:1906.07601, 2019
112019
Investigating adaptation and transfer learning for end-to-end spoken language understanding from speech
N Tomashenko, A Caubrière, Y Estève
102019
State level control for acoustic model training
G Chernykh, M Korenevsky, K Levin, I Ponomareva, N Tomashenko
International Conference on Speech and Computer, 435-442, 2014
102014
Exploration de paramètres acoustiques dérivés de GMMs pour l’adaptation non supervisée de modèles acoustiques à base de réseaux de neurones profonds
N Tomashenko, Y Khokhlov, A Larcher, Y Estève
92016
Speaker verification using spectral and durational segmental characteristics
E Bulgakova, A Sholohov, N Tomashenko, Y Matveev
International conference on speech and computer, 397-404, 2015
92015
Evaluation of feature-space speaker adaptation for end-to-end acoustic models
N Tomashenko, Y Estève
Proceedings of the Eleventh International Conference on Language Resources …, 2018
82018
Exploring GMM-derived features for unsupervised adaptation of deep neural network acoustic models
N Tomashenko, Y Khokhlov, A Larcher, Y Estève
International Conference on Speech and Computer, 304-311, 2016
82016
Метод идентификации дикторов на основе сравнения статистик длительностей фонем
ЕВ Булгакова, АВ Шолохов, НА Томашенко
Научно-технический вестник информационных технологий, механики и оптики 15 (1), 2015
82015
An Investigation of Mixup Training Strategies for Acoustic Models in ASR.
I Medennikov, YY Khokhlov, A Romanenko, D Popov, NA Tomashenko, ...
INTERSPEECH, 2903-2907, 2018
72018
A new perspective on combining GMM and DNN frameworks for speaker adaptation
N Tomashenko, Y Khokhlov, Y Estève
International Conference on Statistical Language and Speech Processing, 120-132, 2016
72016
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20