Sparse Representations in Audio and Music: From Coding to Source Separation

被引：128

作者：

Plumbley, Mark D. ^{[1
]}

Blumensath, Thomas ^{[2
]}

Daudet, Laurent ^{[3
,5
]}

Gribonval, Remi ^{[4
]}

Davies, Mike E. ^{[6
,7
]}

机构：

[1] Queen Mary Univ London, Sch Elect Engn & Comp Sci, London E1 4NS, England

[2] Univ Southampton, Sch Math, Southampton SO17 1BJ, Hants, England

[3] Univ Paris 06, Inst Jean Le Rond Alembert, LAM, F-75015 Paris, France

[4] INRIA, Ctr Inria Rennes Bretagne Atlantique, F-35042 Rennes, France

[5] Univ Denis Diderot Paris 7, Langevin Inst Waves & Images LOA, Paris, France

[6] Univ Edinburgh, Inst Digital Commun IDCOM, Sch Engn & Elect, Edinburgh EH9 3JL, Midlothian, Scotland

[7] Univ Edinburgh, Joint Res Inst Signal & Image Proc, Sch Engn & Elect, Edinburgh EH9 3JL, Midlothian, Scotland

来源：

PROCEEDINGS OF THE IEEE | 2010年 / 98卷 / 06期

基金：

英国工程与自然科学研究理事会;

关键词：

Audio coding; basis functions; discrete cosine transforms; Fourier transforms; music; signal representations; wavelet transforms; BLIND SOURCE SEPARATION; SIGNAL RECOVERY; ALGORITHMS;

D O I：

10.1109/JPROC.2009.2030345

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Sparse representations have proved a powerful tool in the analysis and processing of audio signals and already lie at the heart of popular coding standards such as MP3 and Dolby AAC. In this paper we give an overview of a number of current and emerging applications of sparse representations in areas from audio coding, audio enhancement and music transcription to blind source separation solutions that can solve the "cocktail party problem." In each case we will show how the prior assumption that the audio signals are approximately sparse in some time-frequency representation allows us to address the associated signal processing task.

引用

页码：995 / 1005

页数：11

共 43 条

[1] Unsupervised analysis of polyphonic music by sparse coding [J].

Abdallah, SA ;

Plumbley, MD .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (01) :179-196

[2] Blind separation of dependent sources using the "time-frequency ratio of mixtures" approach [J].

Abrard, F ;

Deville, Y .

SEVENTH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOL 2, PROCEEDINGS, 2003, :81-84

[3] On the uniqueness of overcomplete dictionaries, and a practical way to retrieve them [J].

Aharon, Michal ;

Elad, Michael ;

Bruckstein, Alfred M. .

LINEAR ALGEBRA AND ITS APPLICATIONS, 2006, 416 (01) :48-67

[4]

AMATRIAIN X, 2002, P AES 22 INT C VIRT

[5]

[Anonymous], 2009, WAVELET TOUR SIGNAL

[6]

Arberet S, 2006, LECT NOTES COMPUT SC, V3889, P536

[7] Audio source separation with a single sensor [J].

Benaroya, L ;

Bimbot, F ;

Gribonval, R .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (01) :191-199

[8]

BLUMENSATH T, 2009, APPL COMPUT IN PRESS

[9] Underdetermined blind source separation using sparse representations [J].

Bofill, P ;

Zibulevsky, M .

SIGNAL PROCESSING, 2001, 81 (11) :2353-2362

[10] Atomic decomposition by basis pursuit [J].

Chen, SSB ;

Donoho, DL ;

Saunders, MA .

SIAM JOURNAL ON SCIENTIFIC COMPUTING, 1998, 20 (01) :33-61

← 1 2 3 4 5 →