Villavicencio Fernando (Fernando Villavicencio) - マイポータル

基本情報

所属: 国立情報学研究所

学位: Ph.D(Pierre and Marie Curie University)

J-GLOBAL ID: 201401016354540314
researchmap会員ID: B000242003

外部リンク: https://www.linkedin.com/pub/fernando-villavicencio

研究キーワード

研究分野

情報通信 / 計算科学 / Speech Processing

経歴

2009年10月 - 2014年9月

Yamaha Corporation, Research & Development Division, Research Engineer
2008年6月 - 2009年9月

Pompeu Fabra University, Music Technology Group, Research Engineer / Lecturer
2008年1月 - 2008年6月

IRCAM, Sound Analysis & Synthesis Team, Research Engineer
2001年8月 - 2002年6月

ITESM-GDL (Technological Institute of Superior Studies of Monterrey), Teaching assistant in Digital Systems
2000年8月 - 2002年6月

Autonomous University of Guadalajara, Lecturer on Analog Electronics

学歴

2003年10月 - 2010年3月

Pierre and Marie Curie University - Paris VI, IRCAM (Institute for Research and Acoustic/Music Coordination), Ph.D. program in Informatics, Telecommunications & Electronics
2002年9月 - 2003年9月

University of Rennes I, ENSSAT (Advanced National School of Applied Science and Technology), Master in Signal Processing and Digital Design
1999年7月 - 2002年8月

IPN (National Polytechnic Institute), CINVESTAV-GDL (Center of Research and Advanced Studies), Master in Telecommunications
1995年8月 - 1999年6月

Autonomous University of Guadalajara, Engineering Faculty, Electronics and Communication Engineering

論文

161

Observation-Model Error Compensation For Enhanced Spectral Envelope Transformation In Voice Conversion

Fernando Villavicencio, Jordi Bonada, Yuji Hisaminato

MLSP 2015 2015年9月査読有り
476

Voice Liveness Detection Algorithms Based on Pop Noise Caused by Human Breath for Automatic Speaker Verification

Sayaka, Shiota, Fernando Villavicencio, Junichi Yamagishi, Nobutaka Ono, Isao Echizen, Tomoko Matsui

INTERSPEECH 2015 2015年9月査読有り
281

Efficient Pitch Estimation on Natural Opera-Singing by a Spectral Correlation based Strategy

Fernando Villavicencio, Jordi Bonada, Junichi Yamagishi, Michel Pucher

IEICE Technical Report (IPSJ-SLP-107) 1 2015年7月
130

A strategy for LF-based glottal-source & vocal-tract estimation on stationary modal singing

Fernando Villavicencio

EUSIPCO 2014 (European Signal Processing Conference) 2014年9月査読有り
139

Glottal source model selection for stationary singing-voice by low-band envelope matching

Fernando Villavicencio

NOLISP 2013 (International Conference in Non-Linear Speech Processing) 2013年6月査読有り
103

Non-parallel singing-voice conversion by phoneme-based modeling and covariance approximation

Fernando Villavicencio, Hideki Kenmochi

DAFx 2011 (International Conference on Digital Audio Effects) 2011年9月査読有り
150

Applying Voice Conversion to Concatenative Singing-Voice Synthesis

INTERSPEECH 2010 2010年9月査読有り
119

Resurrecting past singers: non-parallel singing-voice conversion

Fernando Villavicencio, Hideki Kenmochi

InterSinging Workshop 2010年9月査読有り
125

GMM-PCA based Speaker-Timbre Conversion on Full- Quality Speech

Fernando Villavicencio, Esteban Maestre

SSW 2010 (7th Speech Synthesis Workshop) 2010年8月査読有り
85

High-Quilty Voice Conversion

Fernando Villavicencio

IRCAM (Pierre & Marie Curie University) 2010年3月査読有り
99

Applying Improved Spectral Modeling for High- Quality Voice Conversion

Fernando Villavicencio, Axel Röbel, Xavier Rodet

ICASSP 2009 (International Conference on Acoustic, Speech and Signal Processing) 2009年4月査読有り
183

Extending Efficient Spectral Envelope Modeling to Mel-Frequency based Representation

Fernando Villavicencio

ICASSP 2008 (International Conference on Acoustic, Speech and Signal Processing) 2008年4月査読有り
146

On cepstral and all-pole based spectral envelope modeling with unknown model order

Axel Robel, Fernando Villavicencio, Xavier Rodet

PATTERN RECOGNITION LETTERS 28(11) 1343-1350 2007年8月査読有り
215

All-Pole Spectral Envelope Modeling With Order Selection for Harmonic Signals

Fernando Villavicencio, Axel Röbel, Xavier Rodet

ICASSP 2007 (International Conference on Acoustic, Speech and Signal Processing) 2007年4月査読有り
323

Improving LPC Spectral Envelope Extraction of Voiced Speech by True-Envelope Estimation

Fernando Villavicencio, Axel Röbel, Xavier Rodet

ICASSP 2006 (International Conference on Acoustic, Speech and Signal Processing) 2006年5月査読有り

MISC

Vivos Voco: A survey or recent research on voice transformations at IRCAM

Axel Röbel

DAFx 2011 (International Conference on Digital Audio Effects) 2011年9月

書籍等出版物

Transformation et synthèse de la voix parlée et de la voix chantée

Xavier Rodet (担当:分担執筆, 範囲:Parole et Musique)

Odile Jacob 2009年

講演・口頭発表等

On singing voice synthesis and some applications of Voice Transformation

Fernando Villavicencio

Speech Processing Courses in Crete 2015年7月31日 Yannis Stylianou 招待有り
Advances in singing-voice synthesis, transformation and application (co-organizer, co-chair)

Fernando Villavicencio, Keiichi Tokuda, Hideki Kawahara

ICASSP 2012 (International Conference on Acoustic, Speech and Signal Processing) 2012年3月29日
VOCALOID related research at Yamaha’s Speech Technology Group

Fernando Villavicencio

CSTR (Edinburgh); Google labs (London); Trinity College (Dublin); Nagoya University of Arts; Intel Mexico (Guadalajara)
Efficient Envelope Modeling and its application to Voice Conversion

Fernando Villavicencio

Pompeu Fabra University; Tokyo Institute of Technology 招待有り

産業財産権

(in process) Vocal-tract filter modification for vocal intensity transformation

Fernando Villavicencio
(in process) Fully-controllable voice source modeling for voice quality modification

Fernando Villavicencio
(pending) Glottal source and vocal tract filter estimation for stationary singing voice

Fernando Villavicencio
(pending) Estimation of the Voicing Frequency Contour on Speech Signals

Fernando Villavicencio
JP2013242410, US2013311189 Compensation filtering for Voice Conversion

Fernando Villavicencio
JPN083722,US20120065978, EP2431967 Non-parallel singer timbre adaptation for a concatenative singing-voice synthesizer

Fernando Villavicencio
JPN063501 Singer timbre adaptation applied to a concatenative singing-voice synthesizer

Fernando Villavicencio

社会貢献活動

Neanderthal's voice synthesis

寄稿

La Caixa “Once upon a time... the voice!" (Érase una vez...¡el habla!) Spain (country wide exhibition) 2009年 - 2012年