Multiple models integration for multi-environment speech...

Details Multiple models integration for multi-environment speech... Multiple models integration for multi-environment speech...

G - Physics

10

L

G10L 15/20 (2006.01) G10L 15/14 (2006.01)

Patent

CA 2233728

A speech recognition system which effectively recognizes unknown speech from multiple acoustic environments includes a set of secondary models, each associated with one or more particular acoustic environments, integrated with a base set of recognition models. The speech recognition system is trained by making a set of secondary models in a first stage of training, and integrating the set of secondary models with a base set of recognition models in a second stage of training.

Système de reconnaissance de la parole, reconnaissant efficacement une parole inconnue dans de multiples environnements acoustiques. Comprend un ensemble de modèles secondaires associés individuellement à un ou plusieurs environnements acoustiques particuliers et intégrés à un ensemble de base de modèles de reconnaissance. Le système de reconnaissance de la parole est entraîné par création d'un ensemble de modèles secondaires dans une première étape d'entraînement, ces modèles étant intégrés à un ensemble de base de modèles de reconnaissance dans une deuxième étape d'entraînement.

Affiliated with

Also associated with

Rating

Multiple models integration for multi-environment speech... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Multiple models integration for multi-environment speech..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multiple models integration for multi-environment speech... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFCA-PAI-O-1422532