VOICE RECOGNITION SYSTEM USING IMPLICIT SPEAKER ADAPTION

摘要

PROBLEM TO BE SOLVED: To provide a voice recognition method which excellently functions before and during generation of a speaker dependent (SD) acoustic model through unsupervised training. SOLUTION: At least one speaker-independent (SI) acoustic model 230 or 232 is used in combination with at least one speaker-dependent (SD) acoustic model 234 to provide a level of voice recognition performance that at least equals that of the purely SI acoustic model 230 or 232. The disclosed system continually uses unsupervised training to update the acoustic templates in the one or more SD acoustic models. The system then uses the updated SD acoustic models 234 in combination with the at least one SI acoustic model 230 or 232 to provide improved voice recognition performance even during voice recognition testing. COPYRIGHT: (C)2008,JPO&INPIT