Thai Connected Digit Speech Recognition Using Hidden Markov Models

@inproceedings{Deemagarn2004ThaiCD,
  title={Thai Connected Digit Speech Recognition Using Hidden Markov Models},
  author={Amarin Deemagarn and Asanee Kawtrakul},
  year={2004}
}
A Connected digit speech recognition is important in many applications such as voice-dialing telephone, automated banking system, automatic data entry, PIN entry, etc. This research presents speech recognition system of speaker-independent Thai connected digit. The system employs mel frequency cepstrum coefficient (MFCC), delta MFCC, delta-delta MFCC, delta energy and delta-delta energy as features, and applies continuous density hidden Markov model (CDHMM) in the recognition process. The… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 19 CITATIONS

Boosting Thai Syllable Speech Recognition Using Acoustic Models Combination

  • 2008 International Conference on Computer and Electrical Engineering
  • 2008
VIEW 11 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Language Independent Speech Driven Facial Animation

  • 2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems
  • 2008
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Speaker based Language Independent Isolated Speech Recognition System

  • 2015 International Conference on Communication, Information & Computing Technology (ICCICT)
  • 2015
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES

Kawtrakul a “Speakerdependent continuous Thai speech recognition system for e-mail accessing

T. A. Satyapanich
  • In Proceeding of NCSEC
  • 2003
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Syllable-Based connected Thai digit speech recognition using neural network and duration modeling

N Thubthong, B. Kijsirikul
  • In Proceeding of IEEE International Symposium on Intelligent Signal Processing and Communication Systems,
  • 1999
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Improvements in connected digit recognition using higher order spectral and energy features

  • [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing
  • 1991
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Speaker - dependent continuous Thai speech recognition system for e - mail accessing

T. Satyapanich
  • Proceeding of NCSEC
  • 2003

Refined language modeling for Thai continuous speech recognition ”

W. Kasemsiri, C. Kimpan, R. Kongkachandra
  • 2000

Kijsirikul ” Syllable - Based connected Thai digit speech recognition using neural network and duration modeling ”

N Thubthong, B.
  • 1999

A speaker-independent Thai polysyllabic word recognition using hidden Markov model

  • 1997 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, PACRIM. 10 Years Networking the Pacific Rim, 1987-1997
  • 1997