LEARNING A BETTER REPRESENTATION OF SPEECH SOUND WAVES USING RESTRICTED BOLTZMANN MACHINES

Přednášející: Navdeep Jaitly, Autoři: Navdeep Jaitly, Geoffrey Hinton, University of Toronto, Canada

State of the art speech recognition systems rely on pre-processed speech features such as Mel cepstrum or linear predictive coding coefficients that collapse high dimensional speech sound waves into low dimensional encodings. While these have been successfully applied in speech recognition systems, such low dimensional encodings may lose some relevant information and express other information in a way that makes it difficult to use for discrimination. Higher dimensional encodings could both improve performance in recognition tasks, and also be applied to speech synthesis by better modeling the statistical structure of the sound waves. In this paper we present a novel approach for modeling speech sound waves using a Restricted Boltzmann machine (RBM) with a novel type of hidden variable and we report initial results demonstrating phoneme recognition performance better than the current state-of-the-art for methods based on Mel cepstrum coefficients.

Potřebujete Flash Player.

Sdílet:

Stáhnout titulky | Zvětšit video

Nahráno:	2011-05-26 10:30 - 10:50, Club D
Přidáno:	15. 6. 2011 08:59
Počet zhlédnutí:	63
Rozlišení videa:	1024x576 px, 512x288 px
Délka videa:	0:24:35
Audio stopa:	MP3 [8.34 MB], 0:24:35