Noisy speech recognition using variance adapted likelihood measure

Jen-Tzung Chien*, Lee Min Lee, Hsiao Chuan Wang

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

5 Scopus citations

Abstract

Because the norm of testing cepstral vector is shrunk in noisy environment, the model parameters, i.e. mean vector and covariance matrix, should be adapted simultaneously. In this study, we propose a method called variance adapted likelihood measure (VALM) which adapts the mean vector using a projection-based scale factor and adapts the covariance matrix using a variance reduction function estimated from the training database. The variance reduction function can be obtained according to various phonetic units. In the hidden Markov model based experiments, the speech recognition performance is greatly improved by applying VALM. The most significant improvement is achieved when the variance reduction function is separately estimated for different state parameters.

Original languageEnglish
Pages (from-to)45-48
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
StatePublished - 1 Jan 1996
EventProceedings of the 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 6) - Atlanta, GA, USA
Duration: 7 May 199610 May 1996

Fingerprint Dive into the research topics of 'Noisy speech recognition using variance adapted likelihood measure'. Together they form a unique fingerprint.

Cite this