Advances in Nonlinear Speech Processing

1. Front Matter

   PDF

2. Keynote Talks

   1. Multimodal Speech Separation

      • Bertrand Rivet, Jonathon Chambers

      Pages 1-11

   2. Audio Source Separation Using Hierarchical Phase-Invariant Models

      • Emmanuel Vincent

      Pages 12-16

   3. Visual Cortex Performs a Sort of Non-linear ICA

      • Jesús Malo, Valero Laparra

      Pages 17-25

3. Contributed Talks

   1. High Quality Emotional HMM-Based Synthesis in Spanish

      • Xavi Gonzalvo, Paul Taylor, Carlos Monzo, Ignasi Iriondo, Joan Claudi Socoró

      Pages 26-34

   2. Glottal Source Estimation Using an Automatic Chirp Decomposition

      • Thomas Drugman, Baris Bozkurt, Thierry Dutoit

      Pages 35-42

   3. Automatic Classification of Regular vs. Irregular Phonation Types

      • Tamás Bőhm, Zoltán Both, Géza Németh

      Pages 43-50

   4. The Hartley Phase Spectrum as an Assistive Feature for Classification

      • Ioannis Paraskevas, Maria Rangoussi

      Pages 51-59

   5. Speech Enhancement for Automatic Speech Recognition Using Complex Gaussian Mixture Priors for Noise and Speech

      • Ramón F. Astudillo, Eugen Hoffmann, Philipp Mandelartz, Reinhold Orglmeister

      Pages 60-67

   6. Improving Keyword Spotting with a Tandem BLSTM-DBN Architecture

      • Martin Wöllmer, Florian Eyben, Alex Graves, Björn Schuller, Gerhard Rigoll

      Pages 68-75

   7. Score Function for Voice Activity Detection

      • Jordi Solé-Casals, Pere Martí-Puig, Ramon Reig-Bolaño, Vladimir Zaiats

      Pages 76-83

   8. Digital Watermarking: New Speech and Image Applications

      • Marcos Faundez-Zanuy

      Pages 84-89

   9. Advances in Ataxia SCA-2 Diagnosis Using Independent Component Analysis

      • Rodolfo V. García, Fernando Rojas, Carlos G. Puntonet, Belén San Román, Luís Velázquez, Roberto Rodríguez

      Pages 90-94

   10. Spectral Multi-scale Product Analysis for Pitch Estimation from Noisy Speech Signal

       • Mohamed Anouar Ben Messaoud, Aïcha Bouzid, Noureddine Ellouze

       Pages 95-102

   11. Automatic Formant Tracking Method Using Fourier Ridges

       • Imen Jemaa, Kaïs Ouni, Yves Laprie

       Pages 103-110

   12. Robust Features for Speaker-Independent Speech Recognition Based on a Certain Class of Translation-Invariant Transformations

       • Florian Müller, Alfred Mertins

       Pages 111-119

   13. Time-Frequency Features Extraction for Infant Directed Speech Discrimination

       • Ammar Mahdhaoui, Mohamed Chetouani, Loic Kessous

       Pages 120-127

   14. Wavelet Speech Feature Extraction Using Mean Best Basis Algorithm

       • Jakub Gałka, Mariusz Ziółko

       Pages 128-135

   15. Perceptually Motivated Generalized Spectral Subtraction for Speech Enhancement

       • Novlene Zoghlami, Zied Lachiri, Noureddine Ellouze

       Pages 136-143

   16. Coding of Biosignals Using the Discrete Wavelet Decomposition

       • Ramon Reig-Bolaño, Pere Marti-Puig, Jordi Solé-Casals, Vladimir Zaiats, Vicenç Parisi

       Pages 144-151

This volume contains the proceedings of NOLISP 2009, an ISCA Tutorial and Workshop on Non-Linear Speech Processing held at the University of Vic (- talonia, Spain) during June 25-27, 2009. NOLISP2009wasprecededbythreeeditionsofthisbiannualeventheld2003 in Le Croisic (France), 2005 in Barcelona, and 2007 in Paris. The main idea of NOLISP workshops is to present and discuss new ideas, techniques and results related to alternative approaches in speech processing that may depart from the mainstream. In order to work at the front-end of the subject area, the following domains of interest have been de?ned for NOLISP 2009: 1. Non-linear approximation and estimation 2. Non-linear oscillators and predictors 3. Higher-order statistics 4. Independent component analysis 5. Nearest neighbors 6. Neural networks 7. Decision trees 8. Non-parametric models 9. Dynamics for non-linear systems 10. Fractal methods 11. Chaos modeling 12. Non-linear di?erential equations The initiative to organize NOLISP 2009 at the University of Vic (UVic) came from the UVic Research Group on Signal Processing and was supported by the Hardware-Software Research Group. We would like to acknowledge the ?nancial support obtained from the M- istry of Science and Innovation of Spain (MICINN), University of Vic, ISCA, and EURASIP. All contributions to this volume are original. They were subject to a doub- blind refereeing procedure before their acceptance for the workshop and were revised after being presented at NOLISP 2009.

• algorithms
• classification
• component analysis
• decistion trees
• higher-order statistics
• morphology
• nearest neighbour
• neural networks
• non-linear approximation
• non-linear estimation
• non-linear oscillators
• non-linear predictors
• non-parametric models
• speech processing
• speech recognition

• Department of Computer Science, Escola Politecnica Superior, Vic (Barcelona), Spain

  Jordi Solé-Casals, Vladimir Zaiats

Policies and ethics