Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition

  title={Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition},
  author={Yohei Itaya and Heiga Zen and Yoshihiko Nankaku and Chiyomi Miyajima and Keiichi Tokuda and Tadashi Kitamura},
  journal={IEICE Transactions},
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… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 14 extracted citations

Research on text analysis for Tibetan statistical parametric speech synthesis

2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) • 2016
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 11 references

Deterministic annealing EM algorithm

Neural Networks • 1998
View 3 Excerpts
Highly Influenced

Discriminative training for system module integration in speaker and speech recognition

C. Miyajima
Doctoral Dissertation, Nagoya Institute of Technology, • 2001
View 1 Excerpt

MDL - based context - dependent subword modeling for speech recognition

T. Watanabe
J . Acoust . Soc . Jpn . ( E ) • 1995

The use of context in large vocabulary speech recognition

J. J. Odell
View 1 Excerpt

Similar Papers

Loading similar papers…