Bayesian latent variable models for speech recognition

Jen-Tzung Chien, Peng Liu

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

Abstract

We present a Bayesian framework to learn prior and posterior distributions for latent variable models. Our goal is to deal with model regularization and achieve desirable prediction using heterogeneous speech data. A variational Bayesian expectation-maximization algorithm is developed to establish a latent variable model based on the exponential family distributions. This algorithm does not only estimate model parameters but also their hyperparameters which reflect the model uncertainties. The uncertainty is compensated to construct a variety of regularized models. We realize this full Bayesian framework for uncertainty decoding of speech signals. Compared to maximum likelihood method and Bayesian approach with heuristically-selected hyperparameters, the proposed method achieves higher speech recognition accuracy especially in case of sparse and noisy training data.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages7393-7397
Number of pages5
DOIs
StatePublished - 18 Oct 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: 26 May 201331 May 2013

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period26/05/1331/05/13

Keywords

  • Bayesian Learning
  • Exponential Family
  • Latent Variable Model
  • Speech Recognition

Fingerprint Dive into the research topics of 'Bayesian latent variable models for speech recognition'. Together they form a unique fingerprint.

Cite this