Effects of Bayesian predictive classification using variational Bayesian posteriors for sparse training data in speech recognition

Shinji Watanabe, Atsushi Nakamura

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

We introduce a robust classification method using Bayesian predictive distribution (Bayesian predictive classification, referred to as BPC) into speech recognition. We and others have recently proposed a total Bayesian framework for speech recognition, Variational Bayesian Estimation and Clustering for speech recognition (VBEC). VBEC includes an analytical derivation of approximate posterior distributions that are essential for BPC, based on variational Bayes (VB). BPC using VB posterior distributions (VB-BPC) can mitigate the over-training effects by marginalizing output distribution. We address the sparse data problem in speech recognition, and show how VB-BPC is robust against die data sparseness, experimentally.

Original languageEnglish
Pages1105-1108
Number of pages4
Publication statusPublished - 2005 Dec 1
Externally publishedYes
Event9th European Conference on Speech Communication and Technology - Lisbon, Portugal
Duration: 2005 Sep 42005 Sep 8

Conference

Conference9th European Conference on Speech Communication and Technology
CountryPortugal
CityLisbon
Period05/9/405/9/8

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Effects of Bayesian predictive classification using variational Bayesian posteriors for sparse training data in speech recognition'. Together they form a unique fingerprint.

  • Cite this

    Watanabe, S., & Nakamura, A. (2005). Effects of Bayesian predictive classification using variational Bayesian posteriors for sparse training data in speech recognition. 1105-1108. Paper presented at 9th European Conference on Speech Communication and Technology, Lisbon, Portugal.