Faculty of Science and Technology

Hiroyuki SEGI

  (世木 寛之)

Profile Information

Affiliation
Professor, Faculty of Science and Technology Department of Science and Technology , Seikei University
Degree
博士(工学)(慶應義塾大学)

J-GLOBAL ID
201501025877783683
researchmap Member ID
B000244685

Research Interests

 2

Papers

 25
  • Ai Mizota, Hiroyuki Segi
    2021 IEEE International Conference on Consumer Electronics (ICCE), Jan 10, 2021  Peer-reviewed
  • Hiroyuki Segi, Shoei Sato, Kazuo Onoe, Akio Kobayashi, Akio Ando
    Artificial Intelligence: Concepts, Methodologies, Tools, and Applications, 3 2021-2037, Dec 12, 2016  Peer-reviewed
    Tied-mixture HMMs have been proposed as the acoustic model for large-vocabulary continuous speech recognition and have yielded promising results. They share base-distribution and provide more flexibility in choosing the degree of tying than state-clustered HMMs. However, it is unclear which acoustic models to superior to the other under the same training data. Moreover, LBG algorithm and EM algorithm, which are the usual training methods for HMMs, have not been compared. Therefore in this paper, the recognition performance of the respective HMMs and the respective training methods are compared under the same condition. It was found that the number of parameters and the word error rate for both HMMs are equivalent when the number of codebooks is sufficiently large. It was also found that training method using the LBG algorithm achieves a 90% reduction in training time compared to training method using the EM algorithm, without degradation of recognition accuracy.
  • Segi Hiroyuki
    INTERNATIONAL JOURNAL OF MULTIMEDIA DATA ENGINEERING & MANAGEMENT, 7(2) 53-67, Apr, 2016  Peer-reviewed
  • Hiroyuki SEGI
    The Journal of the Faculty of Science and Technology, Seikei University, 52(2) 5-10, Dec, 2015  
  • Hiroyuki Segi, Kazuo Onoe, Shoei Sato, Akio Kobayashi, Akio Ando
    Journal of Information Technology Research, 7(3) 15-31, Jul 1, 2014  Peer-reviewed
    Tied-mixture HMMs have been proposed as the acoustic model for large-vocabulary continuous speech recognition and have yielded promising results. They share base-distribution and provide more flexibility in choosing the degree of tying than state-clustered HMMs. However, it is unclear which acoustic models to superior to the other under the same training data. Moreover, LBG algorithm and EM algorithm, which are the usual training methods for HMMs, have not been compared. Therefore in this paper, the recognition performance of the respective HMMs and the respective training methods are compared under the same condition. It was found that the number of parameters and the word error rate for both HMMs are equivalent when the number of codebooks is sufficiently large. It was also found that training method using the LBG algorithm achieves a 90% reduction in training time compared to training method using the EM algorithm, without degradation of recognition accuracy.

Books and Other Publications

 1
  • 八木伸行監修, 世木寛之ほか著 (Role: Contributor, 第11章音声合成)
    オーム社, Jul, 2008

Presentations

 47

Research Projects

 1

Industrial Property Rights

 72