Title :
Sub-phonetic Polynomial Segment Model for Large Vocabulary Continuous Speech Recognition
Author :
Yeung, Siu-Kei Au ; Li, Chak-Fai ; Siu, Man-Hung
Author_Institution :
Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., China
fDate :
March 18-23, 2005
Keywords :
hidden Markov models; polynomials; signal representation; speech recognition; HMM; K-mean clustering; N-best re-scoring; PSM training; WER; acoustic modeling; clustering triphone model; large vocabulary continuous speech recognition; model sharing; multiple independent segmental unit phoneme representation; sub-phonetic polynomial segment model; top-down clustering; top-down mixture growing methods; Acoustical engineering; Acoustics; Gold; Hidden Markov models; Notice of Violation; Polynomials; Speech recognition; Testing; Training data; Vocabulary;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415083
