The Journal of the Acoustical Society of Korea

The Acoustical Society of Korea (한국음향학회)
권호 표지

A New Method for Segmenting Speech Signal by Frame Averaging Algorithm

  • Byambajav D. (Department of Electronics and Communications Engineering, Kwangwoon University) ;
  • Kang Chul-Ho (Department of Electronics and Communications Engineering, Kwangwoon University)
  • Published : 2005.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

A new algorithm for speech signal segmentation is proposed. This algorithm is based on finding successive similar frames belonging to a segment and represents it by an average spectrum. The speech signal is a slowly time varying signal in the sense that, when examined over a sufficiently short period of time (between 10 and 100 ms), its characteristics are fairly stationary. Generally this approach is based on finding these fairly stationary periods. Advantages of the. algorithm are accurate border decision of segments and simple computation. The automatic segmentations using frame averaging show as much as $82.20\%$ coincided with manually verified segmentation of CMU ARCTIC corpus within time range 16 ms. More than $90\%$ segment boundaries are coincided within a range of 32 ms. Also it can be combined with many types of automatic segmentations (HMM based, acoustic cues or feature based etc.).

Keywords

References

  1. Toledano, DT., Gomez, L.A.H. and Grande, L.V., ' Automatic Phonetic Segmentation' , Speech and Audio Processing, IEEE Transactions, 11, Issue 6, Nov. 2003, 617-625
  2. Wesenick, M.-B and Kipp, A, ' Estimating the Quality of Phonetic Transcriptions and Segmentations of Speech Signals' , Spoken Language, 1996. ICSLP 96. Proceedings, Fourth International Conference 1, 3-6 Oct. 1996, 129-132 vol.1
  3. Kris Demuynck and Tom Laureys, A Comparison of Different Approaches to Automatic Speech Segmentation' , Text, Speech and Dialogue, 5th International Conference, TSD 2002, 277-284
  4. Milone, D.H., Merelo, J.J. and Rufiner, H.L., ' Evolutionary Algorithm for Speech Segmentation' , Evolutionary Computation, 2002. CEC'02. Proceedings of the 2002 Congress, 2, 12-17 May 2002, 1115 -1120
  5. Bridle, J. and Sedgwick, N., ' A Method for Segmenting Acoustic Patterns, with Applications to Automatic Speech Recognition' , Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '77, 2, May 1977, 656-659
  6. Svendsen, T. and Soong, F., ' On the Automatic Segmentation of Speech Signals ' ,Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '87, 12, Apr 1987, 77-80