A neural network controlled adaptive search strategy for HMM-based speech recognition

Authors:
Kouichi Yamaguchi
Affiliations:
ATR Interpreting Telephony Research Laboratories, Kyoto, Japan
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Year:
1993

Citing 4
Cited 0

An efficient augmented-context-free parsing algorithm

Computational Linguistics
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Improvements in beam search for 10000-word continuous speech recognition

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a novel adaptive search method for an HMM-based continuous speech recognition system. 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, we introduce a trainable adaptive search algorithm controlled by a neural network using observable features. This framework has the potential to automatically and dynamically improve 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.