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

Adoram Erell, David Burshtein

Research output: Contribution to journalArticlepeer-review

Abstract

We compare two different approaches to the problem of additive noise in a hidden Markov model (HMM) interbank-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.

Original languageEnglish
Pages (from-to)72-74
Number of pages3
JournalIEEE Transactions on Speech and Audio Processing
Volume5
Issue number1
DOIs
StatePublished - 1997

Fingerprint

Dive into the research topics of 'Noise adaptation of HMM speech récognition systems using tied-mixtures in the spectral domain'. Together they form a unique fingerprint.

Cite this