Application of Zero-Frequency Filtering for Vowel Onset Point Detection

详细信息    查看全文

• 作者：Anil Kumar Vuppala (21)
  
• 关键词：Vowel onset point (VOP) ; Vowels ; zero frequency filtering ; frequency spectrum
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8891
• 期：1
• 页码：172-177
• 全文大小：482 KB
• 参考文献：1. Rao, K.S., Vuppala, A.K.: Non-uniform time scale modification using instants of significant excitation and vowel onset points. Elsevier Speech Communication聽55(6), 745鈥?56 (2013) CrossRef
  2. Prasanna, S.R.M., Reddy, B.V.S., Krishnamoorthy, P.: Vowel onset point detection using source, spectral peaks, and modulation spectrum energies. IEEE Trans. on Audio, Speech, and Language Processing聽17(4), 556鈥?65 (2009) CrossRef
  3. Prasanna, S.R.M., Gangashetty, S.V., Yegnanarayana, B.: Significance of vowel onset point for speech analysis. In: Proc. of Int. Conf. Signal Processing and Communications, Bangalore, India, pp. 81鈥?8 (2001)
  4. Vuppala, A.K., Rao, K.S., Chakrabarti, S.: Improved consonant-vowel recognition for low bit-rate coded speech. Wiley International Journal of Adaptive control and Signal processing聽26(4), 333鈥?49 (2012) CrossRef
  5. Gangashetty, S.V., Sekhar, C.C., Yegnanarayana, B.: Detection of vowel onset points in continuous speech using autoassociative neural network models. In: Proc. Int. Conf. Spoken Language Processing, Jeju Island, Korea, pp. 401鈥?10 (2004)
  6. Vuppala, A.K., Rao, K.S., Chakrabarti, S.: Spotting and recognition of consonant-vowel units from continuous speech using accurate vowel onset points. Springer Circuits, Systems and Signal Processing聽31(4), 1459鈥?474 (2012) CrossRef
  7. Rao, K.S., Yegnanarayana, B.: Duration modification using glottal closure instants and vowel onset points. Speech Communication聽51, 1263鈥?269 (2009) CrossRef
  8. Vuppala, A.K., Rao, K.S.: Speaker identification under background noise using features extracted from steady vowel regions. Wiley International Journal of Adaptive control and Signal processing聽29(9), 781鈥?92 (2013) CrossRef
  9. Vuppala, A.K., Yadav, J., Rao, K.S., Chakrabarti, S.: Vowel onset point detection for low bit rate coded speech. IEEE Transactions on Audio, Speech and Language Processing聽20(6), 1894鈥?903 (2012) CrossRef
  10. Hermes, D.J.: Vowel onset detection. J. Acoust. Soc. Amer.聽87, 866鈥?73 (1990) CrossRef
  11. Wang, J.-F., Wu, C.H., Chang, S.H., Lee, J.Y.: A hierarchical neural network based C/V segmentation algorithm for Mandarin speech recognition. IEEE Trans. on Signal Processing聽39(9), 2141鈥?146 (1991) CrossRef
  12. Wang, J.-H., Chen, S.-H.: A C/V segmentation algorithm for Mandarin speech using wavelet transforms. In: Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Phoenix, Arizona, pp. 1261鈥?264 (1999)
  13. Gangashetty, S.V., Sekhar, C.C., Yegnanarayana, B.: Extraction of fixed dimension patterns from varying duration segments of consonant-vowel utterances. In: Proc. of IEEE ICISIP, pp. 159鈥?64 (2004)
  14. Prasanna, S.R.M., Yegnanarayana, B.: Detection of vowel onset point events using excitation source information. In: Proc. of Interspeech, Lisbon, Portugal, pp. 1133鈥?136 (2005)
  15. Murty, K.S.R., Yegnanarayana, B.: Epoch extraction from speech signals. IEEE Trans. on Audio, Speech, and Language Processing聽16(8), 1602鈥?613 (2008) CrossRef
  16. Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S., Dahlgren, N.L., Zue, V.: TIMIT acoustic-phonetic continuous speech corpus linguistic data consortium. In: Proc. of IEEE ICISIP, Philadelphia, PA (1993)
  
• 作者单位：Anil Kumar Vuppala (21)
  
  21. Language Technologies Research Centre, International Institute of Information Technology, Hyderabad, A.P., India
  
• ISSN：1611-3349

文摘

Vowel onset points in speech signals, are the instances where the voicing of the vowels begin. These points serve as important landmarks for the analysis as well as synthesis of speech signals. These landmarks help to identify the information about the behaviour of transition of several different sounds into and out of the vowel regions. In this paper, we propose a new method to identify vowel onset points for a speech signal using the zero frequency filtered (ZFF) speech signal and its frequency spectrum. The ZFF signal is obtained by passing the speech signal through a resonator with central frequency as 0 Hz. Therefore, ZFF signal essentially contains the low pass components of a given speech signal. Vowels are mostly characterized by the significant energy content in the relatively low frequency bands. Significant improvement in VOP detection performance is observed using proposed method compared to existing methods.