Title :
The SPHINX speech recognition system
Author :
Lee, Kai-Fu ; Hon, Hsiao-Wuen ; Hwang, Mei-Yuh ; Mahajan, S. ; Reddy, Raj
Author_Institution :
Dept. of Comput. Sci., Carnegie-Mellon Univ., Pittsburgh, PA, USA
Abstract :
A description is given of SPHINX an accurate large-vocabulary speaker-independent continuous speech recognition system. The authors have made several recent enhancements, including generalized triphone models, word duration modeling, function-phrase modeling, between-word coarticulation modeling, and corrective training. On the 997-word resource management task, SPHINX attained a word accuracy of 96% with a grammar (perplexity 60), and 82% without grammar (perplexity 997)
Keywords :
speech recognition; SPHINX; between-word coarticulation modeling; continuous speech recognition system; corrective training; function-phrase modeling; generalized triphone models; large vocabulary recognition; perplexity; speaker independent recognition; word duration modeling; Cepstral analysis; Computer science; Filters; Hidden Markov models; Linear predictive coding; Management training; Prototypes; Resource management; Speech recognition; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266459
