Sciweavers

Share
ICANN
2007
Springer

An Application of Recurrent Neural Networks to Discriminative Keyword Spotting

11 years 11 months ago
An Application of Recurrent Neural Networks to Discriminative Keyword Spotting
Abstract. Keyword spotting is a detection task consisting in discovering the presence of specific spoken words in unconstrained speech. The majority of keyword spotting systems are based on generative hidden Markov models and lack discriminative capabilities. However, discriminative keyword spotting systems are based on the estimation of a posteriori probabilities at the frame-level, hence they make use of information from short time spans. This paper presents a discriminative keyword spotting system based on recurrent neural networks only, that uses information from long time spans to estimate keyword probabilities. In a keyword spotting task in a large database of unconstrained speech where an HMM-based speech recogniser achieves a word accuracy of only 65 %, the system achieved a keyword spotting accuracy of 84.5 %.
Santiago Fernández, Alex Graves, Jürge
Added 08 Jun 2010
Updated 08 Jun 2010
Type Conference
Year 2007
Where ICANN
Authors Santiago Fernández, Alex Graves, Jürgen Schmidhuber
Comments (0)
books