Browse > Article

Pre-Processing for Performance Enhancement of Speech Recognition in Digital Communication Systems  

Seo, Jin-Ho (광운대학교 전자공학과)
Park, Ho-Chong (광운대학교 전자공학과)
Publication Information
The Journal of the Acoustical Society of Korea / v.24, no.7, 2005 , pp. 416-422 More about this Journal
Abstract
Speech recognition in digital communication systems has very low performance due to the spectral distortion caused by speech codecs. In this paper, the spectral distortion by speech codecs is analyzed and a pre-processing method which compensates for the spectral distortion is proposed for performance enhancement of speech recognition. Three standard speech codecs. IS-127 EVRC. ITU G.729 CS-ACELP and IS-96 QCELP. are considered for algorithm development and evaluation, and a single method which can be applied commonly to all codecs is developed. The performance of the proposed method is evaluated for three codecs, and by using the speech features extracted from the compensated spectrum. the recognition rate is improved by the maximum of $15.6\%$ compared with that using the degraded speech features.
Keywords
speech recognition; speech codec; digital speech communication; spectral compensation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 3GPP TS 23.228, 'IP Multimedia Subsystem (IMS)', March 2004
2 TIA/EIA/IS-127 'Enhanced variable rate codec. speech service option 3 for wideband spectrum digital systems,' 1996
3 3GPP TS 22.243, 'Speech recognition framework for automated voice services,' Sept. 2003
4 H. Herrnanskv, 'Perceptual linear predictive(PLP) analvsis of speech,' J. Acoust. Society of America, 87, 1738-1752, 1990   DOI   PUBMED
5 ITU G.729, 'Coding of speech at 8kb/s using coniugate-structure algebraic-code-excited linear prediction,' 1996
6 한상욱, 박호종, 'Modified PLP Feature를 적용하여 이동 통신 시스템에서의 음성 인식률 향상', 한국음향학회 추계 학술대회, 고려대학교, 2003
7 TIA/EIA/IS-96, 'Speech service option standard for wideband spread spectrum digital cellular system,' 1994
8 H. K. Kim and R. V. Cox, 'A bitstream-based front-end for wireless speech recognition on IS-136 communications system,' IEEE Trans. Speech and Audio Processing, 9 (5), July 2001