Noise adaptation of HMM speech recognition systems using tied-mixtures in the spectral domain

Author

Erell, Adoram ; Burshtein, David

Author_Institution

DSP Commun., Givat Shmuel, Isreal

Volume

5

Issue

1

fYear

1997

fDate

1/1/1997 12:00:00 AM

Firstpage

72

Lastpage

74

Abstract

We compare two different approaches to the problem of additive noise in a hidden Markov model (HMM) filterbank-based speech recognition system: (i) preprocessing by estimation and (ii) adaptation of the HMM output probability distributions. The adaptation method, previously formulated only for the static spectral features, is generalized in this paper to the time-derivative of the spectrum. Estimation and adaptation are formulated with a common statistical model (MIXMAX) and are compared using the same recognition system. We find that under low and medium signal-to-noise ratio (SNR) conditions, parameter adaptation is superior to preprocessing by estimation

Keywords

band-pass filters; filtering theory; hidden Markov models; noise; parameter estimation; probability; spectral analysis; speech processing; speech recognition; statistical analysis; HMM output probability distributions; HMM speech recognition systems; MIXMAX; MIXMAX adaptation; adaptation method; additive noise; filterbank based speech recognition system; hidden Markov model; noise adaptation; parameter adaptation; preprocessing by estimation; recognition system; signal to noise ratio; spectral domain; static spectral features; statistical model; tied mixtures; time-derivative; Acoustic noise; Discrete Fourier transforms; Filter bank; Hidden Markov models; Noise level; Probability distribution; Prototypes; Quantization; Signal to noise ratio; Speech recognition;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.554271

Filename

554271