A non linear analysis for clean and noisy speech
Date de publication1991
Rouat, Jean; Liu, Yong Chun; Lemieux, Sylvain
Sujet(s)Speech analysis and processing
Abstract: The research in speech analysis is recognized to be an important aspect in the area of speech processing, with applications in speech coding, speech recognition, etc. Depending on the application, the speech analyzer has to extract the most appropriate parameters. The authors focus on the problem of speech analysis with possible applications in speech recognition. It is known that speaker-independent recognition of continuous speech is a very complicated task which has not yet been fully mastered. The better the quality of the analysis, the easier it becomes to recognize what has been spoken. The automatic `demodulation' of speech with nonlinear operators, based on perceptive knowledge is a problem which has not yet been fully addressed, and speech `demodulation' might assist the researcher in the understanding of speech and/or in the design of a simple and efficient speech analysis.
Afficher les documents reliés par le titre, l'auteur et les sujets.
GCC-NMF : séparation et rehaussement de la parole en temps-réel à faible latenceAutre titre : GCC-NMF: low latency real-time speech separation and enhancementWood, Sean (Université de Sherbrooke, 2017)Le phénomène du cocktail party fait référence à notre remarquable capacité à nous concentrer sur une seule voix dans des environnements bruyants. Dans cette thèse, nous concevons, implémentons et évaluons une ...
Bahoura, Mohammed; Rouat, Jean (2006)Abstract : We propose a new speech enhancement method based on time and scale adaptation of wavelet thresholds. The time dependency is introduced by approximating the Teager Energy of the wavelet coefficients, while the ...
Loiselle, Stéphane; Rouat, Jean; Pressnitzer, Daniel; Thorpe, Simon (2005)Speech recognition is very difficult in the context of noisy and corrupted speech. Most conventional techniques need huge databases to estimate speech (or noise) density probabilities to perform recognition. We discuss the ...