Source-dependent text-to-speech system

G - Physics – 10 – L

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

G10L 13/00 (2006.01) G10L 13/08 (2006.01)

Patent

CA 2521440

A method of generating speech from textmessages includes determining a speech feature vector for a voice associated with a source of a text message, and comparing the speech feature vector to speaker models. The method also includes selecting one of the speaker models as a preferred match for the voice based on the comparison, and generating speech from the text message based on the selected speaker model.

La présente invention concerne un procédé permettant la synthèse vocale à partir de messages de texte, procédé pour lequel on détermine un vecteur de caractéristiques vocales pour une voix associée à une source de message de texte, et on compare à des modèles de locuteurs le vecteur de caractéristiques vocales. Le procédé demande également qu'un choisisse l'un des modèles de locuteurs parce que, après comparaison, on considère qu'il correspond le mieux à la voix. Il ne reste plus qu'à générer le signal vocal à partir du message de texte, en utilisant le modèle de locuteur choisi.

LandOfFree

Say what you really think

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

Rating

Source-dependent text-to-speech system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Source-dependent text-to-speech system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Source-dependent text-to-speech system will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFCA-PAI-O-1665664

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