Real-Time Speech Enhancement by Adaptive Spectral Subtraction Method

Abstract:

Non-stationary noise and strong background noise is difficult to extract the actual audio signal problem, an adaptive spectral reduction algorithm is proposed. A dynamic threshold algorithm is devised, iterative update mechanism and the specific implementation are contrived in the clean speech spectrum and noise spectrum estimating. Simulation experiments show that the algorithm can effectively de-noising filter, significantly improve the intelligibility of speech recognition system performance and read, and the method is robust in different noise environments and SNR. The algorithm complexity low, the computational cost is small, real-time, easy to implement, so that the effectiveness and real-time dual meet.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 3774-3778
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.3774
• Online since: May 2014
• Authors: Jing Fang Wang*
• Keywords: Adaptive Processing, Dynamic Threshold, Iterative Spectral Subtraction, Speech Enhancement

References

[1] S. F. Boll, Suppression of acoustic noise in speech using spectral subtraction, [J]. IEEE Trans. ASSP, vol. 27, No. 2, pp. l13-120, (1979).

DOI: 10.1109/tassp.1979.1163209

[2] M. Berouti, R. Schwartz, J. Makhoul, Enhancement of Speech Corrupted by Acoustic Noise, [C]. Proceeding of 1979 IEEE, ICASSP, pp.208-211, (1979).

DOI: 10.1109/icassp.1979.1170788

[3] Y. Epharim, D. Malah, Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator, [J]. IEEE. Trans. Acoustic, Speech Signal Processing, vol. 32, No. 6, pp.1109-1121, (1984).

DOI: 10.1109/tassp.1984.1164453

[4] P. Lochwood, J. Boundy, Experiments with a Nonlinear Spectral Subtractor(NSS), Hidden Markov Models and Projection, for Robust Recongnition in Cars, [J]. Speech Commun., vol. 11, No. 6, pp.215-228, (1992).

DOI: 10.1016/0167-6393(92)90016-z

[5] Y. Ephraim, A minimum mean square error approach for speech enhancement, [J]. Acoustics, Speech, and Signal Processing, vo1. 2, pp.829-832, (1990).

DOI: 10.1109/icassp.1990.115960

[6] Liu Zhibin, Xu Naiping, Speech enhancement based on minimum mean-square error short-time spectral estimation and its realization, [C]. IEEE International conference on intelligent processing system, pp.1794-1797, Oct. (1997).

DOI: 10.1109/icips.1997.669365

[7] R. Martin, Speech enhancement using MMSE short time spectral estimation with Gamma distributed speech priors, [J]. in Proc. IEEE Int. conf. Acoustics , Speech, Signal Processing, vol. 1, pp.253-256, (2002).

DOI: 10.1109/icassp.2002.1005724

[8] S. Kamath, P. Loizou, A multi-band Spectral Subtraction Method for Enhancing Speech Corrupted by Colored Noise, [C]. Proceedings of ICASSP[C]. Orlando USA, IV-4164, (2002).

DOI: 10.1109/icassp.2002.5745591

[9] J. S. Lim and A. V. Oppenheim. Enhancement and Bandwidth Compression of Noisy Speech, [J]. Proc. of the IEEE, vo1. 67, No. 12, pp.1586-1604, Dec. (1979).

DOI: 10.1109/proc.1979.11540

[10] J. D. Gibson, B. Koo, and S. D. Gray, Filtering of Colored Noise for Speech Enhancement and Coding, IEEE Trans. Signal Processing, vol. 39, pp.1732-1742, Aug. (1991).

DOI: 10.1109/78.91144

[11] W. R. Wu and P. C. Chen, Subband Kalman Filtering for Speech Enhancement, [J]. IEEE Trans. On Circuits And Systemsli: Analog And Digital Signal Processing, vol. 45, pp.1072-1083, Aug. (1998).

DOI: 10.1109/82.718814

[12] S. Gannot, D. Burshtein, E. Weinstein, Iterative and sequential Kalman filter-based speech enhancement algorithms, [J]. IEEE Trans Speech and Audio Process, vol. 6, No. 4, pp.373-385, (1998).

DOI: 10.1109/89.701367

[13] Y. Ephraim, H. L. V. Trees, A signal subspace approach for speech enhancement, [J]. IEEE Transactions on Speech and Audio Processing, vol. 3, No. 4, pp.251-266, (1995).

DOI: 10.1109/89.397090

[14] U. Mrital, N. Phamdon, Signal／noise KLT based approach for enhancing speech degraded by colored noise, [J]．IEEE Trans on Speech and Audio Processing, vol. 8, No. 3, pp.159-167, (2000).

DOI: 10.1109/89.824700

[15] A. Rezayee, S. Gazor, An adaptive KLT approach for speech enhancement, [J]. IEEE Tram Speech Audio Processing, vol. 9, No. 2, pp.87-95, (2001).

DOI: 10.1109/89.902276

[16] Y. Hu, P. Loizou, A generalized subspace approach for enhancing speech corrupted by colored noise, [J]. IEEE Trans on Speech and Audio Processing, vol. 11, No. 4, pp.334-341, (2004).

DOI: 10.1109/tsa.2003.814458

[17] H. Leva, Y. Ephraim, Extension of the signal subspace speech enhancement approach to colored noise, [J]. IEEE Signal Processing, vol. 10, No. 4, pp.104-106, (2003).

DOI: 10.1109/lsp.2003.808544

[18] SOON I Y, KOH S N, YEO C K. Noisy speech enhancement using discrete cosine transform[J]. Speech Commun, 1998, 24(3): 249-257.

DOI: 10.1016/s0167-6393(98)00019-3

[19] Brady Laska, Miodrag Bolić, Rafik Goubran, Discrete cosine transform particle filter speech enhancement, Speech Communication, Volume 52, Issue 9, September 2010, Pages 762-775.

DOI: 10.1016/j.specom.2010.05.005

[20] NOIZEUS: A noisy speech corpus for evaluation of speech enhancement algorithms http: /www. utdallas. edu/~loizou/speech/noizeus/ [EB/OL].

[21] Spib Noise data[EB/OL]， http: /spib. rice. edu/spib/select_noise. html.

[22] Ma, J., Hu, Y. and Loizou, P. Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions, Journal of the Acoustical Society of America, 2009，125(5), 3387-3405.

DOI: 10.1121/1.3097493

[23] Hu, Y. and Loizou, P. Evaluation of objective quality measures for speech enhancement, IEEE Transactions on Speech and Audio Processing, 2008，16(1), 229-238.

DOI: 10.1109/tasl.2007.911054

[24] ITU-T(2000). Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codecs, ITU-T Recommendation P. 862.

DOI: 10.1109/icassp.2001.941023

[25] Loizou, P.C.; Gibak Kim; Reasons why Current Speech-Enhancement Algorithms do not Improve Speech Intelligibility and Suggested Solutions; Audio, Speech, and Language Processing, IEEE Transactions on; Issue Date: Jan. 2011; Volume: 19 Issue: 1 ; On page(s): 47 – 56.

DOI: 10.1109/tasl.2010.2045180