This research is concerned for improving the result of speech recognition under the noisy speech. We knew that spectral subtraction and recovery of valleys in spectral envelope obtained from noisy speech are more effective for the improvement of the recognition. In this research, the averaged spectral envelope obtained from vowel spectrums are used for the emphasis of valleys. The vocalic spectral information at lower frequency range is emphasized and the spectrum obtained from consonants is not changed. In simulation, the emphasis coefficients are varied on cepstral domain. This method is used for the recognition of noisy digits and is improved well.
[confproc]
Davis S. B.
/ 1980
/ Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences
/ IEEE Trans. Acoust., Speech Signal Processing
: 357~366
[journal]
J-W. Hung
/ 2001
/ New Approaches for Domain Transformation and Parameter Combination for Improved Accuracy in Parallel Model Combination (PMC) Techniques
/ IEEE Trans. Speech and Audio Processing
9(8)
: 842~855
[confproc]
Kamath, S.
/ 2002
/ A Multiband Spectral Subtraction Method for Enhancing Speech Corrupted by Colored Noise
/ Proc. IEEE Int. Conf. Acoust., Speech Signal Processing
: 101~111
[journal]
Kim, N.S.
/ 2003
/ Speech Recognition under Noisy Environments
/ 나 Telecommunications Review
: 650~661
[web]
ESTI Drafr Standard Doc. Speech Processing
/ Transmission and Quality Aspects (STQ); Distributed Speech Recognition; Front-end Feature Extraction Algorithms; Compression Algorithm
/ http://pda.eti.org/pda/queryform.asp
@article{ART001493790}, author={이광석 and 김현주}, title={Speech Recognition using Spectral Information under Noisy Environments}, journal={Journal of Knowledge Information Technology and Systems}, issn={1975-7700}, year={2010}, volume={5}, number={5}, pages={163-169}
TY - JOUR AU - 이광석 AU - 김현주 TI - Speech Recognition using Spectral Information under Noisy Environments JO - Journal of Knowledge Information Technology and Systems PY - 2010 VL - 5 IS - 5 PB - Korea Knowledge Information Technology Society SP - 163 EP - 169 SN - 1975-7700 AB - This research is concerned for improving the result of speech recognition under the noisy speech. We knew that spectral subtraction and recovery of valleys in spectral envelope obtained from noisy speech are more effective for the improvement of the recognition. In this research, the averaged spectral envelope obtained from vowel spectrums are used for the emphasis of valleys. The vocalic spectral information at lower frequency range is emphasized and the spectrum obtained from consonants is not changed. In simulation, the emphasis coefficients are varied on cepstral domain. This method is used for the recognition of noisy digits and is improved well. KW - Speech Recognition;Noisy Speech Processing;Spectral Envelope;Emphasis Coefficient DO - UR - ER -
이광석 and 김현주. (2010). Speech Recognition using Spectral Information under Noisy Environments. Journal of Knowledge Information Technology and Systems, 5(5), 163-169.
이광석 and 김현주. 2010, "Speech Recognition using Spectral Information under Noisy Environments", Journal of Knowledge Information Technology and Systems, vol.5, no.5 pp.163-169.
이광석, 김현주 "Speech Recognition using Spectral Information under Noisy Environments" Journal of Knowledge Information Technology and Systems 5.5 pp.163-169 (2010) : 163.
이광석, 김현주. Speech Recognition using Spectral Information under Noisy Environments. 2010; 5(5), 163-169.
이광석 and 김현주. "Speech Recognition using Spectral Information under Noisy Environments" Journal of Knowledge Information Technology and Systems 5, no.5 (2010) : 163-169.
이광석; 김현주. Speech Recognition using Spectral Information under Noisy Environments. Journal of Knowledge Information Technology and Systems, 5(5), 163-169.
이광석; 김현주. Speech Recognition using Spectral Information under Noisy Environments. Journal of Knowledge Information Technology and Systems. 2010; 5(5) 163-169.
이광석, 김현주. Speech Recognition using Spectral Information under Noisy Environments. 2010; 5(5), 163-169.
이광석 and 김현주. "Speech Recognition using Spectral Information under Noisy Environments" Journal of Knowledge Information Technology and Systems 5, no.5 (2010) : 163-169.