COMPUTER-IMPLEMENTED METHOD, COMPUTER-READABLE MEDIUM AND SYSTEM FOR PRONUNCIATION LEARNING

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining pronunciations for particular terms. The methods, systems, and apparatus include actions of obtaining audio samples of speech corresponding to a particular term and obtaining candidate...

Full description

Saved in:
Bibliographic Details
Main Authors STROPE, BRIAN PATRICK, LEI, XIN, BEAUFAYS, FRANCOISE, STROHMAN, TREVOR D, PENG, FUCHUN, MENGIBAR, PEDRO J. MORENO
Format Patent
LanguageEnglish
French
Published 31.12.2014
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining pronunciations for particular terms. The methods, systems, and apparatus include actions of obtaining audio samples of speech corresponding to a particular term and obtaining candidate pronunciations for the particular term. Further actions include generating, for each candidate pronunciation for the particular term and audio sample of speech corresponding to the particular term, a score reflecting a level of similarity between of the candidate pronunciation and the audio sample. Additional actions include aggregating the scores for each candidate pronunciation and adding one or more candidate pronunciations for the particular term to a pronunciation lexicon based on the aggregated scores for the candidate pronunciations. La présente invention concerne des procédés, des systèmes et un appareil, comprenant des programmes d'ordinateur codés sur un support de stockage informatique, pour déterminer des prononciations pour des termes particuliers. Les procédés, systèmes et appareil comprennent des actions consistant à obtenir des échantillons audio de parole correspondant à un terme particulier et à obtenir des prononciations candidates pour le terme particulier. D'autres actions consistent à générer, pour chaque prononciation candidate pour le terme particulier et l'échantillon audio de parole correspondant au terme particulier, un score reflétant un niveau de similarité entre la prononciation candidate et l'échantillon audio. Des actions supplémentaires consistent à agréger les scores pour chaque prononciation candidate et à ajouter une ou plusieurs prononciations candidates pour le terme particulier à un lexique de prononciations sur la base des scores agrégés des prononciations candidates.
Bibliography:Application Number: WO2014US31884