Title :
A neural network controlled adaptive search strategy for HMM-based speech recognition
Author :
Yamaguchi, Kouichi
Author_Institution :
ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
Abstract :
A novel adaptive search method for an HMM (hidden Markov model-based continuous speech recognition system is described. A speech recognition system usually uses a heuristic search technique such as a beam search technique requiring a large number of phoneme verifications to achieve optimal search. To reduce this verification overhead and speed up the recognition process, a trainable adaptive search algorithm controlled by a neural network using observable features is introduced. This framework has the potential to improve automatically and dynamically the search mechanism by a neural network training procedure. Experimental comparisons with conventional beam search techniques show that the algorithm is effective in reducing the number of phoneme verifications with little degradation in recognition performance.<>
Keywords :
adaptive control; hidden Markov models; learning (artificial intelligence); neural nets; search problems; speech recognition; HMM-based speech recognition; continuous speech recognition system; hidden Markov model; neural network controlled adaptive search strategy; neural network training procedure; performance; phoneme verifications; trainable adaptive search algorithm; verification overhead;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on
Conference_Location :
Minneapolis, MN, USA
Print_ISBN :
0-7803-7402-9
DOI :
10.1109/ICASSP.1993.319374