TERMINAL DEVICE, SPEECH RECOGNITION METHOD AND SPEECH RECOGNITION PROGRAM

摘要

PROBLEM TO BE SOLVED: To provide a terminal device and a speech recognition processing method capable of realizing both highly accurate speech recognition processing with rich vocabularies and language or acoustic model customization for each user.

SOLUTION: A communication part 101 transmits speech data input from a microphone 102 to a speech recognition server 200 which performs speech recognition. The speech recognition server 200 performs speech recognition processing by using an acoustic model and a language mode, and transmits the result as a speech recognition result to a terminal device 100. When the terminal device 100 receives the speech recognition result from the speech recognition server 200, an assumption revaluation part 106 evaluates the received speech recognition by using the speech data input and the acoustic model and the language model provided to the terminal device 100.

COPYRIGHT: (C)2012,JPO&INPIT