DocumentCode :
813369
Title :
Fast algorithms for phone classification and recognition using segment-based models
Author :
Digalakis, Vassilios V. ; Ostendorf, Mari ; Rohlicek, Jan R.
Author_Institution :
Dept. of Electr., Comput. & Syst. Eng., Boston Univ., MA, USA
Volume :
40
Issue :
12
fYear :
1992
fDate :
12/1/1992 12:00:00 AM
Firstpage :
2885
Lastpage :
2896
Abstract :
Methods for reducing the computation requirements of joint segmentation and recognition of phones using the stochastic segment model are presented. The approach uses a fast segment classification method that reduces computation by a factor of two to four, depending on the confidence of choosing the most probable model. A split-and-merge segmentation algorithm is proposed as an alternative to the typical dynamic programming solution of the segmentation and recognition problem, with computation savings increasing proportionally with model complexity. Although the current recognizer uses context-independent phone models, the results reported for the TIMIT database for speaker-independent joint segmentation and recognition are comparable to those of systems that use context information
Keywords :
speech analysis and processing; speech recognition; stochastic processes; TIMIT database; context-independent phone models; fast algorithms; fast segment classification method; phone classification; phone recognition; speech recognition; split-and-merge segmentation algorithm; stochastic segment model; Classification algorithms; Computational complexity; Context modeling; Gaussian distribution; Hidden Markov models; Neural networks; Speech recognition; State-space methods; Stochastic processes; Vocabulary;
fLanguage :
English
Journal_Title :
Signal Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1053-587X
Type :
jour
DOI :
10.1109/78.175733
Filename :
175733
Link To Document :
بازگشت