Transformation-based Bayesian predictive classification for online environmental learning and robust speech recognition

Jen-Tzung Chien, Guo Hong Liao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

The mismatch between training and testing environments makes the necessity of speech recognizers to be adaptive both in acoustic modeling and decision rule. Accordingly, the speech hidden Markov models (HMM's) should be able to incrementally capture the evolving statistics of environments. Also, the speech recognizer should incorporate the inevitable parameter uncertainty for robust decision. This paper presents a transformation-based Bayesian predictive classification where the uncertainties of transformation parameters of HMM mean vector and precision matrix are adequately represented by a conjugate prior density. Due to the benefit of conjugate density, we generate the reproducible prior/posterior pair such that the hyperparameters of prior density could be evolved successively to new environments using online test data. The evolved hyperparameters could suitably describe the parameter uncertainty for TBPC decision. Therefore, a novel framework of TBPC geared with online prior evolution is developed for robust speech recognition. This framework is examined to be effective and efficient on the recognition task of connected Chinese digits in hands-free car environments.

Original languageEnglish
Title of host publication6th International Conference on Spoken Language Processing, ICSLP 2000
PublisherInternational Speech Communication Association
ISBN (Electronic)7801501144, 9787801501141
StatePublished - 1 Jan 2000
Event6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China
Duration: 16 Oct 200020 Oct 2000

Publication series

Name6th International Conference on Spoken Language Processing, ICSLP 2000

Conference

Conference6th International Conference on Spoken Language Processing, ICSLP 2000
CountryChina
CityBeijing
Period16/10/0020/10/00

Fingerprint Dive into the research topics of 'Transformation-based Bayesian predictive classification for online environmental learning and robust speech recognition'. Together they form a unique fingerprint.

Cite this