On including temporal constraints in Viterbi alignment for speech recognition in noise.

This paper addresses the problem of temporal constraints in the Viterbi algorithm in speaker-dependent and independent tasks. The results here presented suggest that in a speaker-dependent task the introduction of temporal constraints can lead to a high improvement with additive or convolutional noi...

Description complète

Détails bibliographiques
Publié dans:	IEEE Transactions on speech and audio processing 9, 2 (2001).
Auteur principal:	Yoma, N.B
Format:	Article
Langue:	English
Sujets:	Viterbi algorithm. Viterbi alignment. Acoustic model. Additive noise. Computational load. Connected word speech recognition experiments. Convolutional noise. Duration model effect. Max state duration. Min state duration. Noise. Speaker independent task. Speaker-dependent task. Speech recognition. State durations. Statistical modeling. Temporal constraints. Testing conditions. Training conditions. Truncated probability densities. Word position dependent temporal restrictions. Word position independent temporal restrictions.