Speaker-independent dictation of Chinese speech with 32K vocabulary

While early machines adopted isolated syllables as input units and needed boring enrollment, our research focus on the speaker independent, word based dictation. A deliberately designed 120 speaker database was built for training; inter syllable context, tonal and endpoint dependent acoustic model are applied with a promising MFCC feature. Two pass acoustic matching accelerates the recognition, taking full advantage of the monosyllabic structure of Chinese speech. A complete word bigram and trigram serve as language processing module. With all efforts, the system reaches 90% character accuracy, performing in almost real time on a Pentium PC without DSP help