Research biography
Interests
Speech analysis, modelling, modification, conversion, reconstruction and synthesis.
Research works
- PMA-to-speech conversion (samples).
- Reversible speech de-identification via frequency warping and pitch scaling, in collaboration with C. Magariños, P. Lopez-Otero and E. Rodriguez-Banga. Use of watermarking techniques to hide de-identification parameters in speech, in collaboration with A. Valdivielso and I. Hernaez.
- Flexible version of the cesptral-domain radial post-filtering technique.
- Crosslingual cloning of HTS voices, in collaboration with C. Magariños and E. Rodriguez-Banga (samples).
- Assistive applications of speech technologies: ZureTTS (see list of collaborators in publications section).
- Synthesis model surgery techniques to overcome the effects of data scarcity, in collaboration with A. Pierard and T. Dutoit.
- Anti-spoofing based on the detection of synthetic/vocoded signals, in collaboration with J. Sanchez, I. Saratxaga, etc.
- Spectral techniques to enhance the intelligibility of natural and synthetic speech in noise (samples), in collaboration with Y. Stylianou and T.C. Zorila.
- Parametric representation of phase with application to statistical speech synthesis, in collaboration with G. Degottex (samples).
- Parametric voice conversion via frequency warping and amplitude scaling, and its application to rapid adaptation of synthetic voices.
- AHOcoder, a vocoder for statistical parametric speech synthesis and transformation (samples, binary files).
- HMM-based speech synthesis in Basque Language (samples).
- Hybrid synthesis systems (HMM-driven unit selection), in collaboration with I. Sainz.
- Methods to determine the polarity of speech signals using harmonic phases, in collaboration with I. Saratxaga.
- Speaker diarization, in collaboration with I. Luengo, D. Tavarez, etc.
- Emotion conversion through prosodic unit selection (samples).
- Voice conversion algorithms and methods (at UPC-TALP) (samples).
- Harmonic plus stochastic model with constant analysis rate for speech analysis, reconstruction and concatenative synthesis (at UPC-TALP).
- Music analysis-resynthesis using sinusoid plus noise decomposition (at UPNA).
Research projects
- ALIADO, Tecnologías del Habla y del Lenguaje para un Asistente Personal (Spanish Ministry of Science and Technology, TIC2002-04447-C02, 2002-2005)
- TC-STAR, Technology and Corpora for Speech-to-Speech Translation (European Commission, FP6-506738, 2004-2007)
- AVIVAVOZ, Tecnologías para la Traducción de Voz: Reconocimiento, Traducción Estadística Basada en Corpus y Síntesis (Spanish Ministry of Education and Science, TEC2006-13694-C03, 2006-2009)
- TECNOPARLA, Tecnologies de la Parla en Català (Catalan government, 2007-2009)
- ANHITZ, Tecnologías Lingüísticas para la Interacción Multilingüe en Entornos Inteligentes (Basque Government, 2006-2008)
- C-EXTRACTOR, Plataforma de Extracción Automática de Conocimiento a partir de Fuentes de Información Estructuradas (Spanish Ministry of Industry, Tourism and Trade, TSI-020302-2009-4, 2009-2010)
- BERBATEK, Herramientas y Tecnologías para el impulso de la Industria de las Lenguas (Basque Government, IE09-262, 2009-2011)
- BUCEADOR, Búsqueda de Información en Contenidos Audiovisuales Plurilingües (Spanish Ministry of Science and Innovation, TEC2009-14094-C04-02, 2010-2012)
- ZURE_TTS, Sistema para la Obtención de Voces Personalizadas con Aplicación a Personas con Discapacidad Oral (Basque Government, S-PE11UN081, 2011-2012)
- SPEECHTECH4ALL, Investigación Avanzada en Tecnologías del Habla para Aplicación a Entornos Audiovisuales de Interacción Hombre-Máquina Inclusiva (Spanish Ministry of Economy and Competitiveness, TEC2012-38939-C03-03, 2013-2015)
- BER2TEK, Tecnologías de la Lengua, de Voz y Multimedia al servicio de la Industria de las Lenguas (Basque Government, IE12-333, 2012-2014)
- IPARRAHOTSA, Desarrollo de una voz sintética para el euskera estándar de Iparralde (Euroregion Aquitaine-Euskadi, 2012-004, 2013-2014)
- ZURETTS+, Sistema Multilingüe para la Obtención de Voces Sintéticas Personalizadas orientado a Personas con Discapacidad Oral (Basque Government, S-PE13UN154, 2013)
- RESTORE, Reparación, almacenamiento y rehabilitación de la voz (Spanish Ministry of Economy and Competitiveness, TEC2015-67163-C2-1-R, 2016-2018)
Participation in evaluation campaigns
-
TC-STAR Evaluations (voice conversion):
2006,
2007
(best results in cross-lingual category).
-
Albayzin (speech synthesis):
2006
(best results),
2008,
2010
(best results),
2012.
-
Albayzin (diarization, audio segmentation):
2010
(best results),
2012
(best results),
2014
(best results).
-
Blizzard Challenge (speech synthesis):
2007,
2008,
2009,
2011.
-
Hurricane Challenge (speech intelligibility in noise):
2012,
2013
(best results in TTS category for low SNR).
-
Anti-spoofing challenge:
2015.
-
Voice conversion challenge:
2016.
-
Singing synthesis challenge:
2016.
Other professional activities
-
Coordinator of TICRM master at UPV/EHU (june 2013 - september 2015).
-
Invited lecturer:
Speech Processing Courses in Crete SPCC 2015,
máster en Ingeniería Informática at University of Valladolid.
-
Organizing committee member:
general co-chair and project leader in eNTERFACE14 (Bilbao, June-July 2014),
program co-chair in 8th ISCA Speech Synthesis Workshop (Barcelona, September 2013).
-
Journal reviewer:
IEEE Transactions on Audio, Speech and Language Processing,
Speech Communication,
Computer Speech and Language,
EURASIP Journal Audio, Speech and Music Processing,
IEEE Signal Processing Letters,
IEEE Journal of Selected Topics in Signal Processing,
Digital Signal Processing,
Signal, Image and Video Processing,
Neurocomputing,
Applied Sciences,
Multidimensional Systems and Signal Processing.
-
Conference reviewer:
ICASSP (2009, 2012-2017),
Interspeech (2012-2016),
EUSIPCO (2011-2013, 2015-2016),
ASRU (2013, 2015),
SSW (2013),
NoLiSP (2013),
Odyssey (2016),
SLT (2016),
LREC (2014),
Iberspeech (2012, 2014, 2016),
Konvens (2012),
NCC (2014).
-
Evaluation committee member:
RTTH Awards (2011-2013).
-
Session chairman:
Interspeech (2012, 2015),
Iberspeech (2016),
JTH (2008).
-
Doctoral thesis committee member:
I. Saratxaga (UPV/EHU, 2012),
J. Pérez (UPC, 2012),
Y. Tang (UPV/EHU, 2014),
T. Polyakova (UPC, 2015),
M. Koutsogiannaki (UoC, 2015),
J. Sanchez (UPV/EHU, 2016),
D. Tavarez (UPV/EHU, 2016).
-
Student (co-)supervision:
A. Alonso (UPV/EHU, MSc 2013, PhD 2014-...),
C. Magariños (UVigo, PhD 2014-...),
A. Pierard (Erasmus UMons-UPV/EHU, MSc 2015),
A. Valdivielso (UPV/EHU, MSc 2016).
Awards
|
