Table of Content

Open Access iconOpen Access

ARTICLE

Modified Viterbi Scoring for HMM‐Based Speech Recognition

Jihyuck Joa, Han‐Gyu Kimb, In‐Cheol Parka, Bang Chul Jungc, Hoyoung Yooc

a School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea;
b School of Computer Science, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea;
c Department of Electronics Engineering, Chungnam National University, Daejeon, 34134, Republic of Korea

* Corresponding Author: Hoyoung Yoo, email

Intelligent Automation & Soft Computing 2019, 25(2), 351-358. https://doi.org/10.31209/2019.100000096

Abstract

A modified Viterbi scoring procedure is presented in this paper based on Dijkstra’s shortest-path algorithm. In HMM-based speech recognition systems, the Viterbi scoring plays a significant role in finding the best matching model, but its computational complexity is linearly proportional to the number of reference models and their states. Therefore, the complexity is serious in implementing a high-speed speech recognition system. In the proposed method, the Viterbi scoring is translated into the searching of a minimum path, and the shortest-path algorithm is exploited to decrease the computational complexity while preventing the recognition accuracy from deteriorating. In addition, a two-phase comparison structure is proposed to manage state probabilities efficiently. Simulation results show that the proposed method saves computational complexity and recognition time by more than 21% and 10% compared to the conventional Viterbi scoring and the previous early termination, respectively. The improvement of the proposed method becomes significant as the numbers of reference models, states, and Gaussian mixture models increase, which means that the proposed method is more desirable for recent speech recognition systems that deals with complex models.

Keywords


Cite This Article

APA Style
Jo, J., Kim, H., Park, I., Jung, B.C., Yoo, H. (2019). Modified viterbi scoring for hmm‐based speech recognition. Intelligent Automation & Soft Computing, 25(2), 351-358. https://doi.org/10.31209/2019.100000096
Vancouver Style
Jo J, Kim H, Park I, Jung BC, Yoo H. Modified viterbi scoring for hmm‐based speech recognition. Intell Automat Soft Comput . 2019;25(2):351-358 https://doi.org/10.31209/2019.100000096
IEEE Style
J. Jo, H. Kim, I. Park, B.C. Jung, and H. Yoo, “Modified Viterbi Scoring for HMM‐Based Speech Recognition,” Intell. Automat. Soft Comput. , vol. 25, no. 2, pp. 351-358, 2019. https://doi.org/10.31209/2019.100000096



cc Copyright © 2019 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1511

    View

  • 1084

    Download

  • 0

    Like

Related articles

Share Link