Robust training algorithm for adverse speech recognition

Wei Tyng Hong, Sin-Horng Chen

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

In this paper, a new robust training algorithm is proposed for the generation of a set of bias-removed, noise-suppressed reference speech HMM models in adverse environment suffering from both channel bias and additive noise. Its main idea is to incorporate a signal bias-compensation operation and a PMC noise-compensation operation into its iterative training process. This makes the resulting speech HMM models more suitable to the given robust speech recognition method using the same signal bias-compensation and PMC noise-compensation operations in the recognition process. Experimental results showed that the speech HMM models it generated outperformed both the clean-speech HMM models and those generated by the conventional k-means algorithm for two adverse Mandarin speech recognition tasks. So it is a promising robust training algorithm.

Original languageEnglish
Pages (from-to)273-293
Number of pages21
JournalSpeech Communication
Volume30
Issue number4
DOIs
StatePublished - 1 Jan 2000

Fingerprint Dive into the research topics of 'Robust training algorithm for adverse speech recognition'. Together they form a unique fingerprint.

Cite this