Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)

Yohei Itaya, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi KitamuraIEICE 2005

Abstract

This paper investigates the effectiveness of the DAEM (Deterministic Annealing EM) algorithm in acoustic modeling for speaker and speech recognition. Although the EM algorithm has been widely used to approximate the ML estimates, it has the problem of initialization dependence. To relax this problem, the DAEM algorithm has been proposed and confirmed the effectiveness in artificial small tasks. In this paper, we applied the DAEM algorithm to practical speech recognition tasks: speaker recognition based on GMMs and continuous speech recognition based on HMMs. Experimental results show that the DAEM algorithm can improve the recognition performance as compared to the standard EM algorithm with conventional initialization algorithms, especially in the flat start training for continuous speech recognition.
BibTeX
@inproceedings{itaya2005deterministic,
  author = {Yohei Itaya and Heiga Zen and Yoshihiko Nankaku and Chiyomi Miyajima and Keiichi Tokuda and Tadashi Kitamura},
  title = {{Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)}},
  booktitle = {IEICE},
  year = {2005},
}

Loading related content...

Figure