Psychoacoustic model-driven spectral subtraction for monaural speech enhancement

被引：0

作者：

Upadhyay N. ^{[1
]}

机构：

[1] Department of Electronics and Communication Engineering, The LNM Institute of Information Technology, Jaipur

来源：

International Journal of Speech Technology | 2023年 / 26卷 / 04期

关键词：

Adaptive noise estimation; Monaural speech enhancement; Psychoacoustic model; Spectral subtraction;

D O I：

10.1007/s10772-023-10062-9

中图分类号：

学科分类号：

摘要：

In this paper, we investigate a psychoacoustic model-driven spectral subtraction framework for enhancement of noisy speech. In the proposed framework, the noisy speech spectrum is separated into six distinct and unevenly frequency-spaced subbands as per the psychoacoustic model of the human hearing system, and spectral over-subtraction is applied independently in each subband. The noise in each subband is estimated using an adaptive noise estimator that does not require a speech pause tracker. To compute and update the noise, the noisy speech power is adaptively smoothed using a smoothing factor controlled by a posterior SNR. The performance of the proposed framework is evaluated using SNR, segmental SNR (SegSNR), and PESQ scores for a variety of non-stationary and stationary noise environments at varying SNR levels. The experimental results show that the proposed framework outperforms various up-to-date speech enhancement technologies on three extensively used objective metrics assessments and speech spectrograms. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

引用

页码：963 / 979

页数：16

共 23 条

[1]

A Noisy Speech Corpus for Assessment of Speech Enhancement Algorithms, (2007)

[2]

Berouti M., Schwartz R., Makhoul J., Enhancement of speech corrupted by acoustic noise, Proceedings of the International Conference on Acoustic, Speech, Signal Processing, (ICASP), pp. 208-211, (1979)

[3]

Boll S.F., Suppression of acoustic noise in speech using spectral subtraction, IEEE Transaction on Acoustic, Speech, Signal Processing, 27, 2, pp. 113-120, (1979)

[4]

Cohen I., Noise spectrum estimation in adverse environments: Improved minima controlled recursive averaging, IEEE Transaction on Speech and Audio Processing, 11, pp. 466-475, (2003)

[5]

Doblinger G., Computationally efficient speech enhancement by spectral minima tracking in sub-bands, Proceedings of Euro Speech, 2, pp. 1513-1516, (1995)

[6]

Ephraim Y., Statistical-model-based speech enhancement systems, Proceedings of IEEE, 80, 10, pp. 1526-1555, (1992)

[7]

Ephraim Y., Ari H.L., Roberts W., A brief survey of speech enhancement, The Electrical Engineering Handbook (3Rd Ed.), (2006)

[8]

). Ch. 5: Recent advancements in speech enhancement, In the Electrical Engineering Handbook (, pp. 12-26, (2006)

[9]

Kamath S., Loizou P., A multiband spectral subtraction method for enhancing speech corrupted by colored noise, Proceedings of the International Conference on Acoustic, Speech, Signal Processing, (ICASP), (2002)

[10]

Li S., Wang J.Q., Jing X.J., The application of non-linear spectral subtraction method on millimeter wave conducted speech enhancement, Mathematical Problems in Engineering, 2010, pp. 1-12, (2010)

← 1 2 3 →