An automatic pitch-marking method using wavelet transform

This paper describes a new automatic pitch-marking method using wavelet transform. This method detects discontinuity in the speech waveform which occurs at the glottal closure instant (GCI). A time domain prosodic modification technique requires an appropriate determination of the synthesis pitch-marks. We evaluated the performance of the newly developed pitchmarking method by using our internal speech databases with an electroglottograph signal. We achieved 96 percent detection accuracy on the performance evaluation. We confirmed that the proposed pitch-marking method is suitable for waveform concatenation-based synthesis through a listening test using pitch modified speech.

[1]  Eric Moulines,et al.  Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones , 1989, Speech Commun..

[2]  Korris Fu-Lai Chung,et al.  Improving the robustness of wavelet transform for epoch detection , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[3]  Douglas D. O'Shaughnessy,et al.  Automatic and reliable estimation of glottal closure instant and period , 1989, IEEE Trans. Acoust. Speech Signal Process..

[4]  Shubha Kadambe,et al.  Application of the wavelet transform for pitch detection of speech signals , 1992, IEEE Trans. Inf. Theory.

[5]  Masafumi Nishimura,et al.  4. Wavelet Analysis for a Text-to-Speech (TTS) System , 1998 .

[6]  D. Childers,et al.  Two-channel speech analysis , 1986, IEEE Trans. Acoust. Speech Signal Process..

[7]  B. Yegnanarayana,et al.  Epoch extraction of voiced speech , 1975 .