Efficient speech recognition using subvector quantization and discrete-mixture HMMs

Authors:
S. Tsakalidis;V. Digalakis;L. Neumeyer
Affiliations:
Dept. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece;-;-
Venue:
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Year:
1999

Citing 0
Cited 3

A Configurable Logic Based Architecture for Real-Time ContinuousSpeech Recognition Using Hidden Markov Models

Journal of VLSI Signal Processing Systems - Special issue on VLSI on custom computing technology
Reduced feature-set based parallel CHMM speech recognition systems

Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Spoken language analysis, modeling and recognition-statistical and adaptive connectionist approaches
Efficient codebooks for fast and accurate low resource ASR systems

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new form of observation distributions for hidden Markov models (HMMs), combining subvector quantization and mixtures of discrete distributions. We present efficient training and decoding algorithms for the discrete-mixture HMMs (DMHMMs). Our experimental results in the air-travel information domain show that the high-level of recognition accuracy of continuous mixture-density HMMs (CDHMMs) can be maintained at significantly faster decoding speeds. Moreover, we show that when the same number of mixture components is used in DMHMMs and CDHMMs, the new models exhibit superior recognition performance.