標題: BAYESIAN LATENT VARIABLE MODELS FOR SPEECH RECOGNITION
作者: Chien, Jen-Tzung
Liu, Peng
電機資訊學士班
Undergraduate Honors Program of Electrical Engineering and Computer Science
關鍵字: Bayesian Learning;Exponential Family;Latent Variable Model;Speech Recognition
公開日期: 2013
摘要: 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.
URI: http://hdl.handle.net/11536/23537
ISBN: 978-1-4799-0356-6
ISSN: 1520-6149
期刊: 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
起始頁: 7393
結束頁: 7397
Appears in Collections:Conferences Paper