Advertisement

An Improved Endpoint Detection Algorithm Based on Improved Spectral Subtraction with Multi-taper Spectrum and Energy-Zero Ratio

  • Tiantian Bao
  • Yaxin Li
  • Kena Xu
  • Yonghao Wang
  • Wei Hu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10954)

Abstract

Endpoint detection plays a crucial role in speech recognition systems. An effective endpoint detection algorithm can not only reduce the processing time, but also can interfere with the noise of the silent segment. The traditional endpoint detection algorithms are mostly processed in a noise-free environment, so there will be problems such as weak noise immunity. In the problem of low SNR, this paper proposes an improved endpoint detection algorithm based on improved spectral subtraction with multi-taper spectrum and energy-zero ratio. The algorithm uses the improved spectral subtraction method of multi-window spectrum estimation to reduce the speech noise, and then combines the energy-zero ratio with endpoint detection. Experiments show that the proposed algorithm has better robustness under different SNR conditions.

Keywords

Endpoint detection Energy-zero ratio Multi-window spectrum estimation 

References

  1. 1.
    Ying, G.S., Mitchell, C.D., Jamieson, L.H.: Endpoint detection of isolated utterances based on a modified Teager energy measurement. In: IEEE International Conference on Acoustics, Speech, and Signal Processing: Speech Processing, pp. 732–735. IEEE Computer Society (1993)Google Scholar
  2. 2.
    Cao, Y., Gao, J., Yang, G.: Study on speech endpoint detection algorithm based on wavelet energy entropy. In: Control and Decision Conference, pp. 3965–3969. IEEE (2016)Google Scholar
  3. 3.
    Wu, D., Tao, Z., Wu, Y., et al.: Speech endpoint detection in noisy environment using spectrogram boundary factor. In: International Congress on Image and Signal Processing, Biomedical Engineering and Informatics, pp. 964–968. IEEE (2017)Google Scholar
  4. 4.
    Zhang, C., Dong, M.: An improved speech endpoint detection based on adaptive sub-band selection spectral variance. In: Control Conference, pp. 5033–5037. IEEE (2016)Google Scholar
  5. 5.
    Junqua, J.C., Reaves, B., Mak, B.: A study of endpoint detection algorithms in adverse conditions: incidence on a DTW and HMM recognize. In: European Conference on Speech Communication and Technology, Eurospeech 1991, Genova, Italy, September. DBLP, pp. 757–762 (1991)Google Scholar
  6. 6.
    Shin, W.H., Lee, B.S., Lee, Y.K., et al.: Speech/non-speech classification using multiple features for robust endpoint detection. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000, Proceedings, vol. 3, pp. 1399–1402. IEEE (2000)Google Scholar
  7. 7.
    Lynch, J.J., Josenhans, J., Crochiere, R.E.: Speech/Silence segmentation for real-time coding via rule based adaptive endpoint detection. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, pp. 1348–1351. IEEE (1987)Google Scholar
  8. 8.
    Rui, H.U.G., Wei, X.D.: Endpoint detection of noisy speech based on cepstrum. Acta Electronica Sinica 28(10), 95–97 (2000)Google Scholar
  9. 9.
    Wilpon, J.G., Rabiner, L.R.: Application of hidden Markov models to automatic speech endpoint detection. Comput. Speech Lang. 2(3–4), 321–341 (1987)CrossRefGoogle Scholar
  10. 10.
    Huang, L.S., Yang, C.H.: A novel approach to robust speech endpoint detection in car environments. In: IEEE ICASSP-2000, vol. 3, pp. 1751–1754 (2000)Google Scholar
  11. 11.
    Shen, J.L., Hung, J.W., Lee, L.S.: Robust entropy-based endpoint detection for speech recognition in noisy environments. In: International Conference on Spoken Language Processing, Incorporating the, Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, November–December. DBLP (1998)Google Scholar
  12. 12.
    Ramirez, J., Yelamos, P., Gorriz, J.M., et al.: SVM-based speech endpoint detection using contextual speech features. Electron. Lett. 42(7), 426–428 (2006)CrossRefGoogle Scholar
  13. 13.
    Ganapathiraju, A., Hamaker, J., Picone, J.: Support vector machines for speech recognition. In: International Conference on Spoken Language Processing, Incorporating the, Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, November–December, pp. 2348–2355. DBLP (2002)Google Scholar
  14. 14.
    Matsumoto, M., Hori, J.: Classification of silent speech using support vector machine and relevance vector machine. Appl. Soft Comput. 20(7), 95–102 (2014)CrossRefGoogle Scholar
  15. 15.
    Lim, C., Chang, J.H.: Enhancing support vector machine-based speech/music classification using conditional maximum a posteriori criterion. IET Signal Process. 6(4), 335–340 (2012)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Tseng, Y.H., Chiu, T.H., Lin, J.M., et al.: Linear precoding and adaptive multi-taper spectrum detector for cognitive radios. In: International Symposium on VlSI Design, Automation and Test, pp. 1–4. IEEE (2016)Google Scholar
  17. 17.
    Dai, Y.H., Chen, H.C., Qiao, D.J., et al.: Speech endpoint detection algorithm analysis based on short-term energy ratio. Commun. Technol. 42(2), 181–183 (2009)Google Scholar
  18. 18.
    Kumar, S., Phadikar, S., Majumder, K.: Modified segmentation algorithm based on short term energy & zero crossing rate for Maithili speech signal. In: International Conference on Accessibility to Digital World, pp. 169–172. IEEE (2017)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Tiantian Bao
    • 1
    • 3
  • Yaxin Li
    • 1
    • 3
  • Kena Xu
    • 1
    • 3
  • Yonghao Wang
    • 2
    • 3
  • Wei Hu
    • 1
    • 3
  1. 1.College of Computer Science and TechnologyWuhan University of Science and TechnologyWuhanChina
  2. 2.Digital Media Technology LabBirmingham City UniversityBirminghamUK
  3. 3.Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial SystemWuhanChina

Personalised recommendations