首页>
外国专利>
SPEECH RECOGNIZING METHOD, SPEECH INFORMATION RETRIEVAL METHOD, PROGRAM RECORDING MEDIUM, SPEECH RECOGNITION SYSTEM, SERVER COMPUTER FOR SPEECH RECOGNITION, AND SERVER COMPUTER FOR SPEECH INFORMATION RETRIEVAL
SPEECH RECOGNIZING METHOD, SPEECH INFORMATION RETRIEVAL METHOD, PROGRAM RECORDING MEDIUM, SPEECH RECOGNITION SYSTEM, SERVER COMPUTER FOR SPEECH RECOGNITION, AND SERVER COMPUTER FOR SPEECH INFORMATION RETRIEVAL
PROBLEM TO BE SOLVED: To improve the precision of speech recognition by a method for recognizing the speech that a person speaks by a computer by taking not only the speech, but also other factors related to the speech into consideration.;SOLUTION: In a recognition dictionary memory 80 used by a speech recognition part 82, different kinds of speech recognition dictionaries including language models and sound models are previously stored while related to different kinds of attributes of the speaker himself (herself) which are previously assumed and different kinds of attributes of environment wherein the speaker is supposed to be placed when uttering the speech. The speech recognition part 82 selects a language model and a sound model matching the speaker from the recognition dictionary memory 80 according to the actual attributes of the speaker himself (herself) who alters the recognized speech and the attributes of the environment wherein the speaker is actually placed when uttering the speech and uses those selected models to recognize the speech of the speaker.;COPYRIGHT: (C)2002,JPO
展开▼