Title :
Using explicit segmentation to improve HMM phone recognition
Author :
Mitchell, Carl D. ; Harper, Mary P. ; Jamieson, Leah H.
Author_Institution :
Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
Abstract :
We show that many of the errors in a context-dependent phone recognition system are due to poor segmentation. We then suggest a method to incorporate explicit segmentation information directly into the HMM paradigm. The utility of explicit segmentation information is illustrated with experiments involving five types of segmentation information and three methods of smoothing
Keywords :
hidden Markov models; smoothing methods; speech processing; speech recognition; HMM phone recognition; context-dependent phone recognition system; experiments; explicit segmentation; segmentation information; smoothing methods; Acoustic measurements; Cepstral analysis; Context modeling; Cost function; Data mining; Discrete transforms; Hidden Markov models; Smoothing methods; Speech recognition; Upper bound; Viterbi algorithm;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-2431-5
DOI :
10.1109/ICASSP.1995.479406
