System and method for effectively implementing a Mandarin Chinese speech recognition dictionary

A method for performing a speech recognition procedure with an electronic device, comprising the steps of:

• configuring a recognizer to compare input speech data to phone strings from a vocabulary dictionary to thereby generate and output one or more recognized words from said vocabulary dictionary, said vocabulary dictionary being implemented according to an optimized phone set, each of said phone strings being implemented as a sequence of phonemes that are serially configured, said optimized phone set being implemented in a compact manner by utilizing an phonemic and allophonic variation technique that maps different pronunciations of said input speech data to a respective one of said phone strings, said vocabulary dictionary being implemented by utilizing one or more dictionary optimization techniques, said optimized phone set representing sounds of a Mandarin Chinese language without utilizing corresponding tonal information as part of different phones in said optimized phone set, said recognizer thus performing said speech recognition procedure without utilizing any type of tone data to thereby output said one or more recognized words as a final speech recognition result;
• and
• controlling said recognizer with a processor to thereby perform said speech recognition procedure.

A computer-readable medium encoded with a computer program for performing a speech recognition, by performing the steps of:

• configuring a recognizer to compare input speech data to phone strings from a vocabulary dictionary to thereby generate and output one or more recognized words from said vocabulary dictionary, said vocabulary dictionary being implemented according to an optimized phone set, each of said phone strings being implemented as a sequence of phonemes that are serially configured, said optimized phone set being implemented in a compact manner by utilizing a phonemic and allophonic variation technique that maps different pronunciations of said input speech data to a respective one of said phone strings, said vocabulary dictionary being implemented by utilizing one or more dictionary optimization techniques, said optimized phone set representing sounds of a Mandarin Chinese language without utilizing corresponding tonal information as part of different phones in said optimized phone set, said recognizer thus performing said Cantonese speech recognition procedure without utilizing any type of tone data to thereby output said one or more recognized words as a final speech recognition result;
• and
• controlling said recognizer with a processor to thereby perform said speech recognition procedure.

A system for performing a speech recognition procedure with an electronic device, comprising:

• means for comparing input speech data to phone strings from a vocabulary dictionary to thereby generate and output one or more recognized words from said vocabulary dictionary, said vocabulary dictionary being implemented according to an optimized phone set, each of said phone strings being implemented as a sequence of phonemes that are serially configured, said optimized phone set being implemented in a compact manner by utilizing a phonemic and allophonic variation technique that maps different pronunciations of said input speech data to a respective one of said phone strings, said vocabulary dictionary being implemented by utilizing one or more dictionary optimization techniques, said optimized phone set representing sounds of a Mandarin Chinese language without utilizing corresponding tonal information as part of different phones in said optimized phone set, said means for comparing thus performing said speech recognition procedure without utilizing any type of tone data to thereby output said one or more recognized words as a final speech recognition result;
• and
• means for controlling said means for comparing to thereby perform said speech recognition procedure.