Voiced speech blind signal separation algorithm based on signal energy

被引：0

作者：

Li, Hong-Yan ^{[1
]}

Qu, Jun-Ling ^{[1
]}

Zhang, Xue-Ying ^{[1
]}

机构：

[1] College of Information Engineering, Taiyuan University of Technology, Taiyuan

来源：

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2015年 / 45卷 / 05期

关键词：

Auditory segment; Auditory stream; Communication technology; Computational auditory scene analysis; Signal energy; Speech separation;

D O I：

10.13229/j.cnki.jdxbgxb201505041

中图分类号：

学科分类号：

摘要：

Considering the shortcoming of instability and low SNR in existing monaural voiced speech separation algorithms, a new voiced speech separation algorithm based on signal energy is proposed, which introduces the signal energy as another important voiced speech feature. This new algorithm is based on the improvement of the classical Hu-Wang algorithm, applying energy feature to the auditory reorganization part. It further improves the reorganization performance of the target speech auditory stream as well as reduces the influence of noise and improves its stability by applying the energy feature. The experiment results show that compared with Hu-Wang algorithm, this improved algorithm can improve the segmental SNR of the target speech segmentation and improve the separation performance obviously. ©, 2015, Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition). All right reserved.

引用

页码：1665 / 1670

页数：5

共 13 条

[1]

Hu K., Wang D.L., Unvoiced speech segregation from nonspeech interference via CASA and spectral subtraction, IEEE Trans on Audio, Speech and Lang Process, 19, 6, pp. 1600-1609, (2011)

[2]

Hu K., Wang D.L., An unsupervised approach to cochannel speech separation, IEEE Trans on Audio, Speech and Lang Process, 21, 1, pp. 120-129, (2013)

[3]

Hu G.N., Wang D.L., Auditory segmentation based on onset and offset analysis, IEEE Trans on Audio, Speech and Lang Process, 15, 2, pp. 396-405, (2007)

[4]

Narayanan A., Wang D.L., A CASA based system for long-term SNR estimation, IEEE Trans on Audio, Speech and Lang Process, 20, 9, pp. 2518-2527, (2012)

[5]

Wang Y., Han K., Wang D.L., Exploring monaural features for classification-based speech segregation, IEEE Trans on Audio Speech and Lang Process, 21, 2, pp. 270-279, (2013)

[6]

Hu G.N., Wang D.L., A tandem algorithm for pitch estimation and voiced speech segregation, IEEE Trans on Audio Speech and Lang Process, 18, 8, pp. 2067-2079, (2010)

[7]

Li C.-Q., Sun L.-X., Long D., Et al., State and frontiers of research in speech separation, Technical Acoustics, 27, 13, pp. 779-785, (2008)

[8]

Hu G.N., Wang D.L., Monaural speech segregation based on pitch tracking and amplitude modulation, IEEE Trans on Neural Networks, 15, 5, pp. 1135-1150, (2004)

[9]

Zhao L.-H., Wang Z.-F., Monaural voiced speech separation based on harmonic and energy features, Acta Acustica, 37, 2, pp. 218-224, (2012)

[10]

Wang D.L., Brown G.J., Computational Auditory Scene Analysis, (2006)

← 1 2 →