AN ISCA TUTORIAL AND RESEARCH WORKSHOP ON
NON-LINEAR SPEECH PROCESSING

Barcelona, 19-22 April, 2005

 

ORGANIZERS:

 

 

 

 

 


SPONSORS:

 

 

 


 

ORGANIZING COMMITTEE

Marcos Faúndez-Zanuy····································EUPMt, UPC

Jordi Solé Casals··············································UVIC

Léonard Janer Garcia·······································EUPMt, UPC

Josep Roure-Alcobé·········································EUPMt, UPC

Antonio Satué Villar··········································EUPMt, UPC

Virginia Espinosa Duró·····································EUPMt, UPC

 

 

SCIENTIFIC COMMITTEE

Frédéric BIMBOT··············································IRISA, Rennes (France)

Gérard CHOLLET············································ ENST, Paris (France)

Marcos FAÚNDEZ-ZANUY·······························EUPMt, Barcelona (Spain)

Hynek HERMANSKY········································OGI, Portland (USA)

Eric KELLER··························· ·························U. Lausanne (Switzerland)

Bastiaan KLEIJN·············································· KTH, Stockholm (Sweden)

Gernot KUBIN···················································TUG, Graz (Austria)

Jorge LUCERO·················································U. Brasilia (Brasil)

Petros MARAGOS············································N. T. U. Athens (Greece)

Stephen Mc LAUGHLIN··································· U. Edimburgh (UK)

Kuldip PALIWAL·············································· U. Brisbane (Australia)

Bojan PETEK··················································· U. of Ljubljana (Slovenia)

Jean SCHOENTGEN········································U. L. Bruxelles (Belgium)

Jordi SOLÉ-CASALS······································· Universitat de VIC (Spain)

Isabel TRANCOSO·········································· INESC (Portugal)

 

SCIENTIFIC REVIEWERS

Amir Hussain

Andrew Morris

Anna Esposito

Antonio Satue-Villar

Bojan Petek

Dijana Petrovska

Enric Monte Moreno

Erhard Rank

Fernando Díaz-de-María

Gernot Kubin

Jean Rouat

Jean Schoentgen

Jordi Solé-Casals

Léonard Janer

Marcos Faúndez-Zanuy

Peter Murphy

Miguel Ángel Ferrer-Ballester

Mohamed Chetouani

Najim Dehak

Pedro Gómez Vilda

Robert Van Kommer

Yannis Stylianou


 

INDEX

 

History note and presentation

Author

Title

 

page

Marcos Faúndez-Zanuy

NOLISP’2005 Chairman

History note and presentation

 

 

9

 

 

Speaker Recognition I

B. Yegnanarayana, R Kumara Swamy, S. R. Mahadeva Prasanna

Separation of multispeaker speech using excitation information

 

11

 

Asmaa El Hannani, Dijana Petrovska-Delacrétaz

Exploiting High-Level Information Provided by ALISP in Speaker Recognition

 

19

 

Dalei Wu, Andrew C. Morris, Jacques Koreman

MLP internal representation as discriminative features for improved speaker recognition

 

25

 

 

Javier R. Saeta, Javier Hernando

New speaker-dependent threshold estimation method in speaker verification based on weighting scores

 

34

 

 

 

Speech Analysis I

Anna Esposito

Pausing Strategies in Children

 

 

42

Brigitte Zellner Keller

F0 and intensity distributions of Marsec speakers: types of speaker prosody

 

49

 

F.R. Drepper

A two level drive - response model of instationary speech signals

 

58

 

Kihong Kim, Jinkeun Hong, Jongin Lim

Multiresolution sinusoidal speech model using Elliptic band pass filter

 

70

 

 

Voice Pathologies and analysis

Asterios Toutios, Konstantinos Margaritis

On the acoustic-to-electropalatographic mapping

 

 

76

 

J. Schoentgen, E. Dessalle, A. Kacha, F. Grenez

Issues in clinical applications of bidirectional multi-step predictive analysis of speech

 

 

84

 

Jesús B. Alonso, Fernando Díaz-de-María, Carlos M. Travieso, Miguel A. Ferrer

Using nonlinear features for voice disorder detection

 

94

 

Martin Hagmüller, Gernot Kubin

Poincaré sections for pitch mark determination

 

 

107

 

 

Speaker Recognition II

L. Paola García-Perera, Juan A. Nolazco-Flores, and Carlos Mex-Perera

A phoneme-space-representation heuristic to improve the performance in a cryptographic-speech-key generation task

 

 

114

M. Faundez-Zanuy, Martin Hagmüller, Gernot Kubin, Bastiaan Kleijn

The COST-277 speech database

 

122

 

V. Kartik, D. Srikrishna, C. Chandra Sekhar

Speaker change detection using support vector machines

 

130

 

 

Speech Recognition I

Jorge Bernal-Chaves, Carmen Peláez-Moreno, Ascensión Gallardo-Antolín, Fernando Diaz de Maria

Multiclass SVM-Based isolated-digit recognition using a HMM-guided segmentation

 

137

 

 

Giampiero Salvi

Segment boundaries in low latency phonetic recognition

 

145

 

Kevin M. Indrebo, Richard J. Povinelli, and Michael T. Johnson

Third order moments of filtered speech signals for robust speech recognition

 

151

 

 

Voice Pathologies

Juan Ignacio Godino-Llorente,  Pedro Gómez-Vilda, Nicolás Sáenz-Lechón, Manuel Blanco Velasco, Fernando Cruz-Roldán, Miguel Ángel Ferrer Ballester

Discriminative methods for the detection of voice disorders

 

158

 

 

Julien Hanquinet, Francis Grenez, Jean Schoentgen

Synthesis of disordered voices

 

168

 

Pedro Gómez, Rafael Martínez, Francisco Díaz, Carlos Lázaro, Agustín Álvarez, Victoria Rodellar, Víctor Nieto

Estimation of vocal cord biomechanical parameters by non-linear inverse filtering of voice

 

174

 

 

 

 

Applications

Karl Schnell, Arild Lacroix

Voice excitation models for speech production based on time variable Volterra systems

 

184

 

Max Little, Patrick McSharry, Irene Moroz, Stephen Roberts

A Simple Nonlinear Model of Vocal Fold Dynamics for Synthesis and Analysis

 

 

188

 

Jordi Sole-Casals, Enric Monte-Moreno

Source separation techniques applied to blind deconvolution of real world signals

 

204

 

Pavel Rajmic

Method for real-time signal processing via wavelet transform

 

214

 

 

Speech Analysis II

Peter J. Murphy, Olatunji O. Akande

Quantification of glottal and voiced speech harmonics-to-noise ratios using cepstral-based estimation

 

 

224

 

Robert Vich

Pseudo Cepstral Analysis of Czech Vowels

 

233

 

J. M. Gorriz, C. G. Puntonet, J. Ramírez, J. C. Segura

Statistical test for voice activity detection

 

240

 

 

Speech Enchancement

Amir Hussain, Stefano Squartini, Francesco Piazza

Novel subband adaptive systems incorporating Wiener filtering for Binaural speech enhancement

 

 

250

 

Tran Huy Dat, Kazuya Takeda, Fumitada Itakura

The MAP and cumulative distribution function equalization methods for the speech spectral estimation with application in noise suppression filtering

 

259

 

 

Speech Recognition II

Mohamed Chetouani, Amir Hussain, Bruno Gas, Jean-Luc Zarader

New Sub-band Processing Framework using Non-linear Predictive Models for Speech Feature Extraction

 

 

269

 

Casper Store Bonde, Carina Graversen, Andreas Gregers Gregersen, Kim Hoang Ngo, Kim Nørmark, Mikel Purup, Thomas Thorsen and Børge Lindberg

Noise robust automatic speech recognition with adaptive quantile based noise estimation and speech band emphasizing filter band

 

275

 

 

 

Suryakanth V. Gangashetty, C. Chandra Sekhar, B. Yegnanarayana

Spotting multilingual consonant-vowel units of speech using neural networks

 

287

 

 

Special session: COST actions

Marcos Faúndez-Zanuy, Unto Laine, Gernot Kubin, Stephen McLaughlin, Bastiaan Kleijn, Gerard Chollet, Bojan Petek, Amir Hussain

The COST-277 European Action: An overview

 

 

298

 

 

© NOLISP’2005

ISSN: 1680-8908

April 2005

 

CDROM compilation: Marcos Faúndez Zanuy