A new robust forward BSS adaptive algorithm based on automatic voice activity detector for speech quality enhancement

被引：8
作者：
Zoulikha M. [1 ]
Djendi M. [1 ]
机构：
[1] Signal Processing and Image Laboratory (LATSI), University of Blida 1, Route of Soumaa, B.P. 270, Blida
来源：
International Journal of Speech Technology | 2018年 / 21卷 / 04期
关键词：
Adaptive filtering; Blind source separation; Noise reduction; Speech enhancement; Voice activity detection (VAD);
D O I：
10.1007/s10772-018-9555-0
中图分类号：
学科分类号：
摘要：
This paper presents a new adaptive blind source separation (BSS) algorithm for acoustic noise reduction and speech enhancement applications in a car framework. The forward BSS structure is often used to separate speech from noise and enhances the speech signal at the output processing. The drawback of most speech enhancement methods that are based on BSS structures is the use of a manual voice activity detection (VAD) system to control the source separation process. In this work, we propose a new algorithm based on the forward BSS structure and an automatic VAD (AVAD) system. The new AVAD system uses an adaptive approach based on a modified normalized least mean square (NLMS) adaptive algorithm to get a new speech enhancement algorithm. This proposed algorithm allows to: (i) reduce the computational complexity of previous techniques based on AVAD system; (ii) enhance the quality of the output speech signal. We have carried out intensive experiments on the proposed algorithm and others state of the art algorithms that use VAD or AVAD systems. In this paper, we show the efficiency of the proposed algorithm in terms of objective and subjective criteria. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.
引用
收藏
页码：1007 / 1020
页数：13
相关论文
共 47 条
  • [1] Albouy B., Deville Y., Alternative structures and power spectrum criteria for blind segmentation and separation of convolutive speech mixtures, 4Th International Symposium on Independent Component Analysis and Blind Signal Separation (ICA), pp. 361-366, (2003)
  • [2] Al-Kindi M.J., Dunlop J., Improved adaptive noise cancellation in the presence of signal leakage on the noise reference channel, Signal Process, 17, 3, pp. 241-250, (1989)
  • [3] Araki S., Makino S., Aichner R., Nishikawa T., Saruwatari H., Subband based blind source separation with appropriate processing for each frequency band, In 4Th International Symposium on Independent Component Analysis and Blind Signal Separation, pp. 499-504, (2003)
  • [4] Bendoumia R., Djendi M., Variable step-sizes new efficient two-channel backward algorithm for speech intelligibility enhancement: A subband approach, Applied Acoustics, 76, pp. 209-222, (2014)
  • [5] Bouquin-Jeannes R.L., Azirani A.A., Faucon G., Enhancement of speech degraded by coherent and incoherent noise using a cross-spectral estimator, IEEE Transactions on Speech and Audio Processing, 5, pp. 484-487, (1997)
  • [6] Charkani N.H., Auto-adaptive separation of convolutive mixtures, applications to hand-free telephony in cars, (1996)
  • [7] Chien J.T., Lai P.Y., Car speech enhancement using a microphone array, International Journal of Speech Technology, 8, 1, pp. 79-91, (2005)
  • [8] Combescure P., 20 listes de dix phrases phonétiquement équilibrées, Revue d’Acoustique, 56, pp. 34-38, (1981)
  • [9] Darazirar I., Djendi M., A two-sensor Gauss-Seidel fast affine projection algorithm for speech enhancement and acoustic noise reduction, Applied Acoustics, 96, pp. 39-52, (2015)
  • [10] Deller J., Proakis J., Hansen J., Discrete time processing of speech signals, (1993)
12345