A Compressed Sensing Approach to Blind Separation of Speech Mixture Based on a Two-Layer Sparsity Model

Bao, Guangzhao; Ye, Zhongfu; Xu, Xu; Zhou, Yingyue

doi:10.1109/tasl.2012.2234110

Cited by 38 publications

(35 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since speech/interferer signals have better sparsity property in the TF domain compared to the time domain ( Bao, 2013;Bofill and Zibulevsky, 2001 ), the proposed algorithms are performed in the TF domain. Based on that fact, sparsity model based speech enhancement algorithms are almost all performed in the TF domain.…”

Section: Sparsity Model Based Speech Enhancement Algorithms and The Pmentioning

confidence: 99%

Supervised single-channel speech enhancement using ratio mask with joint dictionary learning

Zhang

Bao

Zhang

et al. 2016

Speech Communication

Self Cite

View full text Add to dashboard Cite

Section: Sparsity Model Based Speech Enhancement Algorithms and The Pmentioning

confidence: 99%

Supervised single-channel speech enhancement using ratio mask with joint dictionary learning

Zhang

Bao

Zhang

et al. 2016

Speech Communication

Self Cite

View full text Add to dashboard Cite

“…1(b) can be the DDL or other DL methods. A structured dictionary , which is the concatenation of two sub-dictionaries (3) is learned in all the DL modules.…”

Section: B Scss Schemes and Conventional Approachesmentioning

confidence: 99%

Learning a Discriminative Dictionary for Single-Channel Speech Separation

Bao

2014

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

This paper presents a novel dictionary learning (DL) method to improve the performance of sparsity based single-channel speech separation (SCSS). The conventional approaches regard the sub-dictionaries as independent units and learn sub-dictionaries separately in the short-time Fourier transform (STFT) domain using their corresponding training sets respectively. However, we take the relationship between the sub-dictionaries into account and optimize the sub-dictionaries jointly in the time domain. By satisfying a designed discrimination constraint, a structured dictionary, whose atoms have better correspondences to the speaker labels, is learned so that the sources can be recovered by the corresponding reconstruction after sparse coding. An algorithm, which consists of sparse coding stage and dictionary updating stage, is proposed to deal with this DL optimization problem. Two strategies, i.e., direct learning and adaptive learning, are presented to select the training sets which are used to learn the discriminative dictionary. Experimental results show that the proposed SCSS algorithms have superior performance compared with other tested approaches.

show abstract

“…The number of clusters is equal to the number of sources, and the cluster center is calculated for each category of data to estimate the mixing matrix. Further, a cluster center modification algorithm based on Hough transform is developed to improve the accuracy of the estimated mixing matrix [22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Novel mixing matrix estimation approach in underdetermined blind source separation

Sun

Wen

et al. 2016

Neurocomputing

View full text Add to dashboard Cite

A Compressed Sensing Approach to Blind Separation of Speech Mixture Based on a Two-Layer Sparsity Model

Cited by 38 publications

References 25 publications

Supervised single-channel speech enhancement using ratio mask with joint dictionary learning

Supervised single-channel speech enhancement using ratio mask with joint dictionary learning

Learning a Discriminative Dictionary for Single-Channel Speech Separation

Novel mixing matrix estimation approach in underdetermined blind source separation

Contact Info

Product

Resources

About