Oscar Saz
Oscar Saz
Data Scientist at BioCatch Ltd
Adresse e-mail validée de biocatch.com
Titre
Citée par
Citée par
Année
The MGB challenge: Evaluating multi-genre broadcast media recognition
P Bell, MJF Gales, T Hain, J Kilgour, P Lanchantin, X Liu, A McParland, ...
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
1242015
Tools and technologies for computer-aided speech and language therapy
O Saz, SC Yin, E Lleida, R Rose, C Vaquero, WR Rodríguez
Speech Communication 51 (10), 948-967, 2009
1102009
VOCALIZA: An application for computer-aided speech therapy in Spanish language
C Vaquero, O Saz, E Lleida, J Marcos, C Canalís, CP De Educación
IV Jornadas en Tecnología del Habla, 321-326, 2006
502006
Cepstral vector normalization based on stereo data for robust speech recognition
L Buera, E Lleida, A Miguel, A Ortega, Ó Saz
IEEE transactions on audio, speech, and language processing 15 (3), 1098-1113, 2007
482007
E-inclusion technologies for the speech handicapped
C Vaquero, O Saz, E Lleida, WR Rodriguez
2008 IEEE International Conference on Acoustics, Speech and Signal …, 2008
322008
Automatic transcription of multi-genre media archives
P Lanchantin, PJ Bell, M Gales, T Hain, X Liu, Y Long, J Quinnell, ...
302013
A prelingual tool for the education of altered voices
WR Rodríguez, O Saz, E Lleida
Speech Communication 54 (5), 583-600, 2012
282012
Unsupervised data-driven feature vector normalization with acoustic model adaptation for robust speech recognition
L Buera, A Miguel, Ó Saz, A Ortega, E Lleida
IEEE transactions on audio, speech, and language processing 18 (2), 296-309, 2009
272009
Silla de ruedas inteligente controlada por voz
J Minguez, JM Alcubierre, L Montesano, L Montano, O Saz, E Lleida
Primer Congreso Internacional de Domótica, Robótica y Teleasistencia para Todos, 2007
26*2007
Combining feature and model-based adaptation of RNNLMs for multi-genre broadcast speech recognition
S Deena, M Hasan, M Doulaty, O Saz, T Hain
Proceedings of the Annual Conference of the International Speech …, 2016
242016
The 2015 Sheffield system for transcription of multi-genre broadcast media
O Saz, M Doulaty, S Deena, R Milner, RWM Ng, M Hasan, Y Liu, T Hain
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
242015
Comunica-tools for speech and language therapy
W Rodríguez, O Saz, E Lleida, C Vaquero, A Escartín
First Workshop on Child, Computer and Interaction, 2008
242008
Speech technology applied to children with speech disorders
WRR Dueñas, C Vaquero, O Saz, E Lleida
4th Kuala Lumpur International Conference on Biomedical Engineering 2008 …, 2008
212008
Measuring the impact of translation on the accuracy and fluency of vocabulary acquisition of English
O Saz, Y Lin, M Eskenazi
Computer Speech & Language 31 (1), 49-64, 2015
202015
A study of pronunciation verification in a speech therapy application
SC Yin, R Rose, O Saz, E Lleida
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
202009
Analysis of acoustic features in speakers with cognitive disorders and speech impairments
O Saz, J Simón, WR Rodríguez, E Lleida, C Vaquero
EURASIP Journal on Advances in Signal Processing 2009, 1-11, 2009
172009
A novel corpus of children’s impaired speech
O Saz, WR Rodrıguez, E Lleida, C Vaquero
Proceedings of the 2008 Workshop on Children, Computer and Interaction …, 2008
17*2008
The 2015 Sheffield system for longitudinal diarisation of broadcast media
R Milner, O Saz, S Deena, M Doulaty, RWM Ng, T Hain
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
162015
Verifying pronunciation accuracy from speakers with neuromuscular disorders
SC Yin, RC Rose, O Saz, E Lleida
Ninth Annual Conference of the International Speech Communication Association, 2008
152008
Capturing local variability for speaker normalization in speech recognition
A Miguel, E Lleida, R Rose, L Buera, Ó Saz, A Ortega
IEEE transactions on audio, speech, and language processing 16 (3), 578-593, 2008
132008
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20