Sixth International Conference on Spoken Language Processing
October 16-20, 2000
Speech Recognition Using HMMs with Quantized Parameters
Speech and Audio Systems Laboratory, Nokia Research Center,
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.
Vasilache, Marcel (2000):
"Speech recognition using HMMs with quantized parameters",
In ICSLP-2000, vol.1, 441-444.