Sciweavers

147 search results - page 5 / 30
» Independent component analysis for noisy speech recognition
Sort
View
ICA
2004
Springer
14 years 3 months ago
Independent Slow Feature Analysis and Nonlinear Blind Source Separation
We present independent slow feature analysis as a new method for nonlinear blind source separation. It circumvents the indeterminacy of nonlinear independent component analysis by ...
Tobias Blaschke, Laurenz Wiskott
ICASSP
2011
IEEE
13 years 1 months ago
A time-warping framework for speech turbulence-noise component estimation during aperiodic phonation
The accurate estimation of turbulence noise affects many areas of speech processing including separate modification of the noise component, analysis of degree of speech aspiration...
Nicolas Malyska, Thomas F. Quatieri
ICASSP
2008
IEEE
14 years 4 months ago
Maximum likelihood approach to speech enhancement for noisy reverberant signals
This paper proposes a speech enhancement method for signals contaminated by room reverberation and additive background noise. The following conditions are assumed: (1) The spectra...
Takuya Yoshioka, Tomohiro Nakatani, Takafumi Hikic...
ESANN
2007
13 years 11 months ago
A hierarchical model for syllable recognition
Inspired by recent findings on the similarities between the primary auditory and visual cortex we propose a neural network for speech recognition based on a hierarchical feedforw...
Xavier Domont, Martin Heckmann, Heiko Wersing, Fra...
NIPS
2000
13 years 11 months ago
Periodic Component Analysis: An Eigenvalue Method for Representing Periodic Structure in Speech
An eigenvalue method is developed for analyzing periodic structure in speech. Signals are analyzed by a matrix diagonalization reminiscent of methods for principal component analy...
Lawrence K. Saul, Jont B. Allen