Endpoint Detection of Speech Signal Using Wavelet Transform

웨이브렛 변환을 이용한 음성신호의 끝점검출

  • 석종원 (경북대학교 전자·전기공학부) ;
  • 배건성 (경북대학교 전자·전기공학부)
  • Published : 1999.08.01

Abstract

In this paper, we investigated the robust endpoint detection algorithm in noisy environment. A new feature parameter based on a discrete wavelet transform is proposed for word boundary detection of isolated utterances. The sum of standard deviation of wavelet coefficients in the third coarse and weighted first detailed scale is defined as a new feature parameter for endpoint detection. We then developed a new and robust endpoint detection algorithm using the feature found in the wavelet domain. For the performance evaluation, we evaluated the detection accuracy and the average recognition error rate due to endpoint detection in an HMM-based recognition system across several signal-to-noise ratios and noise conditions.

본 논문에서는 잡음이 포함된 음성의 시작점과 끝점을 효율적으로 검출할 수 있는 알고리듬에 대하여 연구하였다. 이를 위해, 웨이브렛 영역에서의 에너지 분포를 고려함으로써 잡음환경하에서도 음성을 검출할 수 있는 새로운 검출 파라미터를 제안하였다. 제안된 끝점검출 파라미터는 웨이브렛 영역에서 세 번째 coarsed 스케일의 표준편차와 가중치를 곱한 첫 번째 detailed 스케일의 표준편차의 합으로 정의하였다. 제안된 끝점검출기의 성능평가를 위해서 다양한 SNR에서 기존방식과 비교하여 시작점과 끝점의 정확도 실험을 수행하였고 HMM 음성인식시스템을 이용하여 인식실험도 수행하였다.

Keywords

References

  1. Bell Syst. Tech. J. v.54 no.2 An Algorithm for Determining the Endpoints of Isolated Utterances L. R. Rabiner;M. R. Sambur
  2. IEEE Trans. Acoust., Speech, and Signal Processing v.ASSP-29 no.4 An improved endpoint detector for isolated word recognition L.F. Lamel(et. al.)
  3. IEEE Trans. Acoust., Speech, and Signal Processing v.2 no.3 A Robust Algorithm for Word Boundary Detection in the Presence of Noise Jean-Claude Junqua;Brian Mak;Ben Reave
  4. Pro. IEEE ICASSP-90 On a simple algorithm to calculate the 'energy' of a signal J. F. Kaiser
  5. Proc. IEEE ICASSP - 93 Endpoint detection of isolated utterancesbased on a modified teager energy measurement G.S. Ying;C.D. Mitchell;L.H. Jamieson
  6. IEEE Trans. on Info. Theory v.36 no.5 The Wavelet Transform Time FrequencyL-ocalization and Signal Analysis I. Daubechies
  7. IEEE Signal Processing Magazine wavelet and Signal Processing O. Rioul;M. Vetterli
  8. Signal Processing v.6 no.2 Multi-dimensional Sub-band Coding M. Vetterli
  9. Ten Lectures on wavelets I. Daubechies
  10. Speech Communication v.8 no.1 A Robust Algorithm for Accurate Endpointing of Speech Signals M. H. Savoji
  11. Proc. IEEE ICASSP An improved speech detection algorithm for isolated Korean utterances M. Han;C. K. Park