Combining multi-section Bayesian template with level-building algorithm for robust connected Mandarin digit recognition

Ruey Ching Shyu, Jhing Fa Wang, Chaug Ching Huang, Chung Hsien Wu, Jyh Shing Shyuu, Jau Yien Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A robust connected Mandarin digit recognition system based on multi-section Bayesian templates and the level-building algorithm is presented in this paper. In the multi-section Bayesian template, both coarticulation effects and the characteristics of the digit itself can be properly exhibited. In particular, each section is organized into a Bayesian template which is characterized by a powerful statistical framework. In the recognition phase, several factors such as finding a more desirable lower and upper bound of input speech length, word duration checking and post-processing are carefully considered to make the proposed system more robust. The proposed system is tested using a multi-speaker database (25 males, 25 females) and a string accuracy of 95.4 % is achieved.

Original languageEnglish
Title of host publication1993 International Symposium on VLSI Technology, Systems, and Applications, VLSI-TSA 1993 - Proceedings of Technical Papers
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages213-217
Number of pages5
ISBN (Electronic)0780309782
DOIs
Publication statusPublished - 1993 Jan 1
Event1993 International Symposium on VLSI Technology, Systems, and Applications, VLSI-TSA 1993 - Taipei, Taiwan
Duration: 1993 May 121993 May 14

Publication series

NameInternational Symposium on VLSI Technology, Systems, and Applications, Proceedings
ISSN (Print)1930-8868

Conference

Conference1993 International Symposium on VLSI Technology, Systems, and Applications, VLSI-TSA 1993
CountryTaiwan
CityTaipei
Period93-05-1293-05-14

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Combining multi-section Bayesian template with level-building algorithm for robust connected Mandarin digit recognition'. Together they form a unique fingerprint.

  • Cite this

    Shyu, R. C., Wang, J. F., Huang, C. C., Wu, C. H., Shyuu, J. S., & Lee, J. Y. (1993). Combining multi-section Bayesian template with level-building algorithm for robust connected Mandarin digit recognition. In 1993 International Symposium on VLSI Technology, Systems, and Applications, VLSI-TSA 1993 - Proceedings of Technical Papers (pp. 213-217). [263603] (International Symposium on VLSI Technology, Systems, and Applications, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VTSA.1993.263603