Method and apparatus for adapting the language model's size...

G - Physics – 10 – L

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

G10L 15/18 (2006.01)

Patent

CA 2203132

Disclosed are a method and an apparatus for adapting, particularly reducing, the size of a language model, which comprises word n-grams, in a speech recognition system. The invention provides a mechanism to discard those n-grams for which the acoustic part of the system requires less support from the language model to recognize correctly. The proposed method is suitable for identifying those trigrams in a language model for the purpose of discarding during the built-time of the system. Provided is also another automatic classification scheme for words which allows the compression of a language model, but under retention of accuracy. Moreover it allows an efficient usage of sparsely available text corpora because even singleton trigrams are used when they are helpful. No additional software tools are needed to be developed because the main tool, the fast match scoring, is a module readily available in the known recognizers themselves. Further improvement of the method is accomplished by classification of words according to the common text in which they occur as far as they distinguish from each other acoustically. The invention opens the possibility to make speech recognition available in low-cost personal computers (PC's), even in portable computers like Laptops.

On décrit un procédé ainsi qu'un appareil d'adaptation, notamment de réduction, de la dimension d'un modèle de langage comprenant un nombre n de grammes de mots, dans un système de reconnaissance vocale. L'invention concerne un mécanisme destiné à laisser de côté ces nombres n de grammes pour la reconnaissance correcte desquels la partie acoustique du système nécessite un soutien moindre du modèle de langage. Le procédé proposé convient à l'identification des trigrammes d'un modèle de langage, dans le but de pouvoir les laisser de côté pendant le temps de mise en oeuvre du système. On décrit également un autre système de classification automatique des mots, lequel permet la compression d'un modèle de langage, mais sous réserve de justesse, ainsi qu'en outre un usage efficace de corpus de texte disponibles de manière éparse, car même des trigrammes formant un singleton sont utilisés lorsque nécessaires. Aucun outil logiciel supplémentaire n'a besoin d'être développé car l'outil principal, à savoir la segmentation d'appariement rapide, consiste en un module facilement disponible dans les dispositifs connus de reconnaissance. Une amélioration ultérieure du procédé consiste à accomplir la classification des mots selon le texte commun dans lequel ils surviennent, pour autant qu'ils se distinguent les uns des autres sur le plan acoustique. L'invention rend possible la mise en oeuvre de la reconnaissance vocale dans des ordinateurs personnels bon marché, même dans des ordinateurs portatifs.

LandOfFree

Say what you really think

Search LandOfFree.com for Canadian inventors and patents. Rate them and share your experience with other people.

Rating

Method and apparatus for adapting the language model's size... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for adapting the language model's size..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for adapting the language model's size... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFCA-PAI-O-1993479

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.