In this paper we describe the structure and examine the performance of a recognition engine based on hidden Markov models (HMMs) with quantized parameters (qHMM). The main goal of qHMMs is to enable a low complexity implementation without sacrificing the classification performance. In the tests with a whole word digit dialler engine and a phoneme based isolated word recognizer we managed to preserve the performance of unquantized HMMs with qHMMs having as little as 5 bit for a mean component and 3 bit for a variance component.
Cite as: Vasilache, M. (2000) Speech recognition using HMMs with quantized parameters. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 1, 441-444, doi: 10.21437/ICSLP.2000-109
@inproceedings{vasilache00_icslp,
author={Marcel Vasilache},
title={{Speech recognition using HMMs with quantized parameters}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 1, 441-444},
doi={10.21437/ICSLP.2000-109}
}