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

被引：127

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 50 条

[41] Coding overcomplete representations of audio using the MCLT
Yoon, Byung-Jun
Malvar, Henrique S.
DCC: 2008 DATA COMPRESSION CONFERENCE, PROCEEDINGS, 2008, : 152 - +
[42] Sparse pursuit and dictionary learning for blind source separation in polyphonic music recordings
Sören Schulze
Emily J. King
EURASIP Journal on Audio, Speech, and Music Processing, 2021
[43] Sparse pursuit and dictionary learning for blind source separation in polyphonic music recordings
Schulze, Soeren
King, Emily J.
EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2021, 2021 (01)
[44] Time-Frequency Representations for Single-Channel Music Source Separation
Tan, Vanessa H.
de Leon, Franz
2019 INTERNATIONAL SYMPOSIUM ON MULTIMEDIA AND COMMUNICATION TECHNOLOGY (ISMAC), 2019,
[45] Persian Music Source Separation in Audio-Visual Data Using Deep Learning
Hashemi, Seyedeh Sogand
Aghabozorgi, Masoudreza
Sadeghi, Mohammad Taghi
2020 6TH IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2020,
[46] Semi-blind Source Separation via Sparse Representations and Online Dictionary Learning
Rambhatla, Sirisha
Haupt, Jarvis
2013 ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, 2013, : 1687 - 1691
[47] INFORMED SOURCE SEPARATION: SOURCE CODING MEETS SOURCE SEPARATION
Ozerov, Alexey
Liutkus, Antoine
Badeau, Roland
Richard, Gael
2011 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA), 2011, : 257 - 260
[48] Music retiler: Using NMF2D source separation for audio mosaicing
Aarabi, Hadrien Foroughmand
Peeters, Geoffroy
2018 CONFERENCE ON INTERACTION WITH SOUND (AUDIO MOSTLY): SOUND IN IMMERSION AND EMOTION (AM'18), 2018,
[49] Learning Word Representations with Hierarchical Sparse Coding
Yogatama, Dani
Faruqui, Manaal
Dyer, Chris
Smith, Noah A.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 87 - 96
[50] ROBUST UNDERDETERMINED BLIND AUDIO SOURCE SEPARATION OF SPARSE SIGNALS IN THE TIME-FREQUENCY DOMAIN
Sbai, Si Mohamed Aziz
Aissa-El-Bey, Abdeldjalil
Pastor, Dominique
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 3716 - 3719

← 1 2 3 4 5 →