ISCA Archive NOLISP 2007 Sessions
  ISCA Archive Sessions

ITRW on Nonlinear Speech Processing

Paris, France
22-25 May 2007

Contributed Papers

HMM-based Spanish speech synthesis using CBR as F0 estimator
Xavi Gonzalvo, Ignasi Iriondo, Joan Claudi Socoró, Francesc Alías, Carlos Monzo

A wavelet-based technique towards a more natural sounding synthesized speech
Mehmet Atas, Süleyman Baykut, Tayfun Akgül

Objective and subjective evaluation of an expressive speech corpus
Ignasi Iriondo, Santiago Planet, Joan-Claudi Socoró, Francesc Alías

On the usefulness of linear and nonlinear prediction residual signals for speaker recognition
Marcos Faundez-Zanuy

Multi-filter-bank approach for speaker verification based on genetic algorithm
Christophe Charbuillet, Bruno Gas, Mohamed Chetouani, Jean Luc Zarader

Speaker recognition via nonlinear discriminant features
Lara Stoll, Joe Frankel, Nikki Mirghafori

Bispectrum mel-frequency cepstrum coefficients for robust speaker identification
Ufuk Ülüg, Tolga Esat Özkurt, Tayfun Akgül

Perceptron-based class verification
Michael Gerber, Tobias Kaufmann, Beat Pfister

Manifold learning-based feature transformation for phone classification
Andrew Errity, John McKenna, Barry Kirkpatrick

Word recognition with a hierarchical neural network
Xavier Domont, Martin Heckmann, Heiko Wersing, Frank Joublin, Stefan Menzel, Bernhard Sendhoff, Christian Goerick

Discriminative keyword spotting
Joseph Keshet, David Grangier, Samy Bengio

Hybrid models for automatic speech recognition: a comparison of classical ANN and kernel-based methods
Ana I. García-Moral, Rubén Solera-Urena, Carmen Peláez-Moreno, Fernando Díaz-de-María

Towards phonetically-driven hidden Markov models: can we incorporate phonetic landmarks in HMM-based ASR?
Guillaume Gravier, Daniel Moraru

A hybrid genetic-neural front-end extension for robust speech recognition over telephone lines
Sid-Ahmed Selouani, Habib Hamam, Douglas O’Shaughnessy

Estimating the stability and dispersion of the biometric glottal fingerprint in continuous speech
P. Gómez, A. Álvarez, L. M. Mazaira, R. Fernández, V. Rodellar

Trajectory mixture density network with multiple mixtures for acoustic-articulatory inversion
Korin Richmond

Application of feature subset selection based on evolutionary algorithms for automatic emotion recognition in speech
Aitor Álvarez, Idoia Cearreta, Juan Miguel López, Andoni Arruti, Elena Lazkano, Basilio Sierra, Nestor Garay

Non-stationary self-consistent acoustic objects as atoms of voiced speech
Friedhelm R. Drepper

The Hartley phase cepstrum as a tool for signal analysis
I. Paraskevas, E. Chilton, M. Rangoussi

Quantitative perceptual separation of two kinds of degradation in speech denoising applications
Anis Ben Aicha, Sofia Ben Jebara

Threshold reduction for improving sparse coding shrinkage performance in speech enhancement
Neda Faraji, S. M. Ahadi, S. Saloomeh Shariati

Efficient Viterbi algorithms for lexical tree based models
S. España-Boquera, M.J. Castro-Bleda, F. Zamora-Mart´ýnez, J. Gorbe-Moya

Acoustic units selection in Chinese-English bilingual speech recognition
Lin Yang, Jianping Zhang, Yonghong Yan

Tone recognition in Mandarin spontaneous speech
Zhaojie Liu, Pengyuan Zhang, Jian Shao, Qingwei Zhao, Yonghong Yan (1) Ji Feng

Evaluation of a feature selection scheme on ICA-based filter- bank for speech recognition
Neda Faraji, S. M. Ahadi

A robust endpoint detection algorithm based on identification of the noise nature
Denilson C. Silva

EMD analysis of speech signal in voiced mode
Aïcha Bouzid, Noureddine Ellouze

Estimation of speech features of glottal excitation by nonlinear prediction
Karl Schnell, Arild Lacroix

An efficient VAD based on a generalized Gaussian PDF
O. Pernía, J. M. Gúrriz, J. Ramírez, C. G. Puntonet, I. Turias


Invited Papers

Contributed Papers