A New Keyword Spotting Approach Based on Reward Function

Yassine Benayed (1) , Dominique Fohr (1) , Jean-Paul Haton (1) , Gérard Chollet (2)

1 PAROLE - Analysis, perception and recognition of speech
2 LHC - Laboratoire Hubert Curien

In this paper, we compare the performance achieved by different word-spotting techniques based on hidden Markov models. We propose two methods to detect keywords, the first one uses a GMM (Gaussian Mixture Model) as a filler model to absorb the out-of-vocabulary words. The second is an alternative approach which does not attempt to model out-of-vocabulary words, instead, it uses buckled phonemes basedgrammar. Furthermore, it uses different reward functions to favourite the recognition of the keywords phonemes.

Mots clés: gmm; out-of-vocabulary words; mots hors-vocabualire; modèle poubelle; filler model; modèles de markov cachés; hidden markov models

Domaines: Autre [cs.OH]

Yassine Benayed, Dominique Fohr, Jean-Paul Haton, Gérard Chollet. A New Keyword Spotting Approach Based on Reward Function. Eventh International Symposium on Signal Processing and Its Applications - ISSPA'2003, Jul 2003, Paris, France, 4 p. ⟨inria-00099707⟩