Speech Enhancement Using Compressed Sensing

被引：0

作者：

Abrol, Vinayak ^{[1
]}

Sharma, Pulkit ^{[2
]}

Sao, Anil Kumar ^{[2
]}

机构：

[1] Panjab Univ, UIET, Chandigarh, India

[2] IIT Mandi, Mandi, India

来源：

14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5 | 2013年

关键词：

Speech Processing; Compressed Sensing; Sparse Basis; Speech Enhancement; SIGNAL RECONSTRUCTION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes an approach based on the compressed sensing for speech enhancement. It attempts to exploit the fact that it is relatively easy to find sparse representation for speech signal but the same cannot hold true for noise. Thus for a given speech signal a sparse vector is derived which extracts the speech signal from the given noisy speech signal. Approach is further modified to ensure the speech enhancement across the varying segments of speech signal, which is present due to language, emotion and speech uttered by a person. Experimental results show that the proposed approach can be an alternative to the existing approaches for speech enhancement.

引用

页码：3273 / 3277

页数：5

共 21 条

[1]

Abrol V, 2013, IEEE INT ADV COMPUT, P1159

[2] Robust uncertainty principles:: Exact signal reconstruction from highly incomplete frequency information [J].

Candès, EJ ;

Romberg, J ;

Tao, T .

IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (02) :489-509

[3]

Christensen Mads Graesboll, 2009, 2009 43rd Asilomar Conference on Signals, Systems and Computers, P356, DOI 10.1109/ACSSC.2009.5469828

[4] Compressed sensing [J].

Donoho, DL .

IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (04) :1289-1306

[5]

Elad M, 2010, SPARSE AND REDUNDANT REPRESENTATIONS, P3, DOI 10.1007/978-1-4419-7011-4_1

[6] STATISTICAL-MODEL-BASED SPEECH ENHANCEMENT SYSTEMS [J].

EPHRAIM, Y .

PROCEEDINGS OF THE IEEE, 1992, 80 (10) :1526-1555

[7]

EPHRAIM Y, 2005, CRC ELECT ENG HDB

[8]

Gannot S, 2005, SIG COM TEC, P161, DOI 10.1007/3-540-27489-8_8

[9]

Gesen Zhang, 2010, Proceedings of the 2010 International Conference on Information and Automation (ICIA 2010), P455, DOI 10.1109/ICINFA.2010.5512379

[10] A modified A priori SNR for speech enhancement using spectral subtraction rules [J].

Hasan, MK ;

Salahuddin, S ;

Khan, MR .

IEEE SIGNAL PROCESSING LETTERS, 2004, 11 (04) :450-453

← 1 2 3 →