Monaural Music Source Separation Using Convolutional Sparse Coding
We present a comprehensive performance study of a new time-domain approach for estimating the components of an observed monaural audio mixture. Unlike existing time-frequency approaches that use the product of a set of spectral templates and their corresponding activation patterns to approximate the...
Saved in:
Published in | IEEE/ACM transactions on audio, speech, and language processing Vol. 24; no. 11; pp. 2158 - 2170 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
01.11.2016
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) IEEE - ACM |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | We present a comprehensive performance study of a new time-domain approach for estimating the components of an observed monaural audio mixture. Unlike existing time-frequency approaches that use the product of a set of spectral templates and their corresponding activation patterns to approximate the spectrogram of the mixture, the proposed approach uses the sum of a set of convolutions of estimated activations with prelearned dictionary filters to approximate the audio mixture directly in the time domain. The approximation problem can be solved by an efficient convolutional sparse coding algorithm. The effectiveness of this approach for source separation of musical audio has been demonstrated in our prior work, but under rather restricted and controlled conditions, requiring the musical score of the mixture being informed a priori and little mismatch between the dictionary filters and the source signals. In this paper, we report an evaluation that considers wider, and more practical, experimental settings. This includes the use of an audio-based multipitch estimation algorithm to replace the musical score, and an external dataset of audio single notes to construct the dictionary filters. Our result shows that the proposed approach remains effective with a larger dictionary, and compares favorably with the state-of-the-art nonnegative matrix factorization approach. However, in the absence of the score and in the case of a small dictionary, our approach may not be better. |
---|---|
AbstractList | We present a comprehensive performance study of a new time-domain approach for estimating the components of an observed monaural audio mixture. Unlike existing time-frequency approaches that use the product of a set of spectral templates and their corresponding activation patterns to approximate the spectrogram of the mixture, the proposed approach uses the sum of a set of convolutions of estimated activations with prelearned dictionary filters to approximate the audio mixture directly in the time domain. The approximation problem can be solved by an efficient convolutional sparse coding algorithm. The effectiveness of this approach for source separation of musical audio has been demonstrated in our prior work, but under rather restricted and controlled conditions, requiring the musical score of the mixture being informed a priori and little mismatch between the dictionary filters and the source signals. In this paper, we report an evaluation that considers wider, and more practical, experimental settings. This includes the use of an audio-based multipitch estimation algorithm to replace the musical score, and an external dataset of audio single notes to construct the dictionary filters. Here, our result shows that the proposed approach remains effective with a larger dictionary, and compares favorably with the state-of-the-art nonnegative matrix factorization approach. However, in the absence of the score and in the case of a small dictionary, our approach may not be better. We present a comprehensive performance study of a new time-domain approach for estimating the components of an observed monaural audio mixture. Unlike existing time-frequency approaches that use the product of a set of spectral templates and their corresponding activation patterns to approximate the spectrogram of the mixture, the proposed approach uses the sum of a set of convolutions of estimated activations with prelearned dictionary filters to approximate the audio mixture directly in the time domain. The approximation problem can be solved by an efficient convolutional sparse coding algorithm. The effectiveness of this approach for source separation of musical audio has been demonstrated in our prior work, but under rather restricted and controlled conditions, requiring the musical score of the mixture being informed a priori and little mismatch between the dictionary filters and the source signals. In this paper, we report an evaluation that considers wider, and more practical, experimental settings. This includes the use of an audio-based multipitch estimation algorithm to replace the musical score, and an external dataset of audio single notes to construct the dictionary filters. Our result shows that the proposed approach remains effective with a larger dictionary, and compares favorably with the state-of-the-art nonnegative matrix factorization approach. However, in the absence of the score and in the case of a small dictionary, our approach may not be better. |
Author | Li Su Ping-Keng Jao Yi-Hsuan Yang Wohlberg, Brendt |
Author_xml | – sequence: 1 surname: Ping-Keng Jao fullname: Ping-Keng Jao email: nafraw@citi.sinica.edu.tw organization: Res. Center for Inf. Technol. Innovation, Taipei, Taiwan – sequence: 2 surname: Li Su fullname: Li Su email: lisu@citi.sinica.edu.tw organization: Res. Center for Inf. Technol. Innovation, Taipei, Taiwan – sequence: 3 surname: Yi-Hsuan Yang fullname: Yi-Hsuan Yang email: yang@citi.sinica.edu.tw organization: Res. Center for Inf. Technol. Innovation, Taipei, Taiwan – sequence: 4 givenname: Brendt surname: Wohlberg fullname: Wohlberg, Brendt email: brendt@lanl.gov organization: Los Alamos Nat. Lab., Los Alamos, NM, USA |
BackLink | https://www.osti.gov/servlets/purl/1495128$$D View this record in Osti.gov |
BookMark | eNpdkEtPwzAQhC0EEgX6B-ASwYVLi9ePuD6WipdUBFLbs-U4GwhK7RInSPx7XAocOO1q55uVZo7Ivg8eCTkFOgag-mo5Xcyfx4xCPmZSTzjje2TAONMjzanY_92ZpodkGOMbpRSo0lqJAbl-DN72rW2yxz7WLluEvnWYLXBjW9vVwWerWPuXbBb8R2j67SWxi6RGTMcyaSfkoLJNxOHPPCar25vl7H40f7p7mE3nI8e17kZFUYIodInOSQmAvHASHKAStmRlYW0JTFSVxJQgV05RcJVSoirzPAdlGT8m57u_IXa1ia7u0L264D26zoDQEtgkQZc7aNOG9x5jZ9Z1dNg01mPoo4GJlHwilM4TevEPfUvhU7wtxalmAFwniu0o14YYW6zMpq3Xtv00QM22fvNdv9nWb37qT6aznalGxD-DkpxLEPwL5JqBzg |
CODEN | ITASD8 |
CitedBy_id | crossref_primary_10_1016_j_sigpro_2019_107379 crossref_primary_10_1007_s11042_018_7060_8 crossref_primary_10_1109_TNNLS_2019_2906074 crossref_primary_10_1109_LWC_2019_2930693 crossref_primary_10_1109_TSP_2021_3064181 crossref_primary_10_1109_LSP_2021_3135196 crossref_primary_10_1109_TIP_2019_2896541 crossref_primary_10_12677_CSA_2022_1212283 crossref_primary_10_1002_wics_1646 crossref_primary_10_1109_LSP_2018_2847236 crossref_primary_10_1109_ACCESS_2019_2950423 |
Cites_doi | 10.1109/MSP.2013.2297715 10.1109/ICASSP.2009.4959531 10.1109/TSA.2005.858005 10.1109/LSP.2010.2042530 10.1109/ICASSP.2014.6854953 10.1109/MSP.2013.2296076 10.1109/ICASSP.2013.6637775 10.1109/TASLP.2013.2285484 10.1109/TMM.2012.2191398 10.1109/CVPR.2010.5539957 10.1109/TASLP.2015.2442411 10.1109/CVPR.2010.5539958 10.1109/ICASSP.2013.6637745 10.1109/ICASSP.2014.6853676 10.1201/b17758 10.1016/j.sigpro.2005.06.007 10.1109/ICASSP.2015.7178034 10.1109/ICASSP.2013.6637607 10.1109/ICASSP.2012.6289134 10.1109/TIP.2015.2495260 10.1002/cpa.20132 10.1109/JSTSP.2011.2159701 10.1137/S1064827596304010 10.1109/ICASSP.2013.6637776 10.1109/LSP.2015.2433061 10.1109/TASL.2011.2172425 10.1109/ICASSP.2014.6855053 10.1109/TASL.2006.885253 10.1109/ICASSP.2015.7177967 10.1109/ICASSP.2012.6287834 10.1109/MSP.2012.2208663 10.1109/ASPAA.2009.5346542 10.1109/TASLP.2015.2450494 10.1162/neco.2008.04-08-771 10.1109/TASLP.2014.2362006 10.1109/TASL.2011.2109379 10.1109/LSP.2016.2514845 10.1109/TASL.2007.914120 10.1002/cpa.20124 10.1109/ICIP.2016.7532675 10.1109/TASL.2009.2034186 10.1109/ICASSP.2015.7177937 10.1038/44565 10.1109/ICASSP.2016.7471637 10.1109/ICASSP.2011.5946389 10.1561/2200000016 10.1109/MSP.2012.2205029 10.1007/978-3-540-30110-3_63 10.1007/s10844-013-0258-3 10.1109/ICASSP.2015.7178063 10.1111/j.1467-9868.2005.00532.x 10.1109/ICASSP.2009.4960364 10.1109/MLSP.2015.7324332 10.1109/LSP.2015.2466447 10.1109/ICASSP.2014.6854992 10.1109/TASL.2009.2020886 10.1109/ICASSP.2010.5495699 10.1007/11679363_87 10.1109/TSA.2005.860346 10.1109/ASPAA.2003.1285860 10.1109/CVPR.2013.57 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2016 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2016 |
CorporateAuthor | Los Alamos National Lab. (LANL), Los Alamos, NM (United States) |
CorporateAuthor_xml | – name: Los Alamos National Lab. (LANL), Los Alamos, NM (United States) |
DBID | 97E RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D OIOZB OTOTI |
DOI | 10.1109/TASLP.2016.2598323 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional OSTI.GOV - Hybrid OSTI.GOV |
DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Computer and Information Systems Abstracts Computer and Information Systems Abstracts |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Music Mathematics Computer Science |
EISSN | 2329-9304 |
EndPage | 2170 |
ExternalDocumentID | 1495128 4223528231 10_1109_TASLP_2016_2598323 7533514 |
Genre | orig-research |
GrantInformation_xml | – fundername: Academia Sinica Career Development Program – fundername: National Science Council of Taiwan grantid: MOST102-2221-E-001-004-MY3 funderid: 10.13039/501100001868 |
GroupedDBID | 0R~ 4.4 6IK 97E AAJGR AAKMM AALFJ AASAJ AAWTV ABQJQ ABVLG ACIWK ACM ADBCU ADPZR AEBYY AENSD AFWIH AFWXC AIKLT AKJIK ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CCLIF EBS EJD GUFHI HGAVV IFIPE IPLJI JAVBF LHSKQ M43 OCL PQQKQ RIA RIE RNS ROL AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D ABGDV ABQDU ACATF ADHRN AFJFK ATWAV OIOZB OTOTI PQEST |
ID | FETCH-LOGICAL-c399t-bbd14b9decc5511e3bc51c1e74ad2dbaad124ff5e98367c701cf774fd66617a23 |
IEDL.DBID | RIE |
ISSN | 2329-9290 |
IngestDate | Fri May 19 01:07:38 EDT 2023 Fri Aug 16 04:26:16 EDT 2024 Thu Oct 10 16:53:59 EDT 2024 Fri Aug 23 00:55:33 EDT 2024 Wed Jun 26 19:22:23 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 11 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c399t-bbd14b9decc5511e3bc51c1e74ad2dbaad124ff5e98367c701cf774fd66617a23 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 USDOE Laboratory Directed Research and Development (LDRD) Program LA-UR-15-27928 89233218CNA000001 |
ORCID | 0000000247671843 |
OpenAccessLink | https://www.osti.gov/servlets/purl/1495128 |
PQID | 1830921139 |
PQPubID | 85426 |
PageCount | 13 |
ParticipantIDs | osti_scitechconnect_1495128 crossref_primary_10_1109_TASLP_2016_2598323 proquest_journals_1830921139 ieee_primary_7533514 proquest_miscellaneous_1855384796 |
PublicationCentury | 2000 |
PublicationDate | 2016-11-01 |
PublicationDateYYYYMMDD | 2016-11-01 |
PublicationDate_xml | – month: 11 year: 2016 text: 2016-11-01 day: 01 |
PublicationDecade | 2010 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway – name: United States |
PublicationTitle | IEEE/ACM transactions on audio, speech, and language processing |
PublicationTitleAbbrev | TASLP |
PublicationYear | 2016 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) IEEE - ACM |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) – name: IEEE - ACM |
References | ref56 ref12 ref59 ref15 ref58 ref14 ref53 ref52 ref10 ref17 ref16 (ref79) 2011 lewicki (ref65) 1999; 11 ref18 cerón (ref55) 2014 fitzgerald (ref86) 2012 li (ref54) 2009; 17 smaragdis (ref11) 0 yoshii (ref13) 0 ref51 ref50 chen (ref78) 0 lee (ref57) 1999; 401 ref46 ref45 ref47 ref42 ref41 bosch (ref38) 0 ref88 ref44 ref87 ref49 smaragdis (ref84) 2004 ref8 ref7 ref9 ref3 paulus (ref71) 0 ref6 ref5 ref82 ref40 benetos (ref85) 0 pedersen (ref74) 2007 mørup (ref68) 2008 ref35 wohlberg (ref81) 2016 ref34 ref36 ref75 ref30 ref77 ref76 woodruff (ref31) 0 ref1 ref39 gómez (ref43) 0 (ref83) 2010 itoyama (ref32) 0 rish (ref19) 2014 goto (ref80) 0; 3 joder (ref48) 0 ref70 ref73 ref72 heittola (ref37) 0 ref24 ref67 ref23 ref26 ref69 ref20 roux (ref61) 2010 gnann (ref63) 0 ref66 fitzgerald (ref2) 0 ref22 ref21 sturmel (ref64) 2012 ref28 ref27 ref29 wang (ref4) 0 ref60 kong (ref25) 2014 ref62 vembu (ref33) 0 |
References_xml | – ident: ref12 doi: 10.1109/MSP.2013.2297715 – year: 2012 ident: ref86 article-title: On the use of masking filters in sound source separation publication-title: Proc Int Conf Digital Audio Effects contributor: fullname: fitzgerald – start-page: 625 year: 0 ident: ref71 article-title: State of the art report: Audio-based music structure analysis publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: paulus – year: 2014 ident: ref25 article-title: Fast convolutional sparse coding (FCSC) contributor: fullname: kong – ident: ref34 doi: 10.1109/ICASSP.2009.4959531 – ident: ref82 doi: 10.1109/TSA.2005.858005 – ident: ref62 doi: 10.1109/LSP.2010.2042530 – ident: ref72 doi: 10.1109/ICASSP.2014.6854953 – start-page: 133 year: 0 ident: ref32 article-title: Instrument equalizer for query-by-example retrieval: Improving sound source separation based on integrated harmonic and inharmonic models publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: itoyama – ident: ref50 doi: 10.1109/MSP.2013.2296076 – start-page: 601 year: 0 ident: ref43 article-title: Predominant fundamental frequency estimation vs singing voice separation for the automatic transcription of accompanied flamenco singing publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: gómez – ident: ref53 doi: 10.1109/ICASSP.2013.6637775 – ident: ref30 doi: 10.1109/TASLP.2013.2285484 – ident: ref27 doi: 10.1109/TMM.2012.2191398 – ident: ref20 doi: 10.1109/CVPR.2010.5539957 – ident: ref28 doi: 10.1109/TASLP.2015.2442411 – ident: ref21 doi: 10.1109/CVPR.2010.5539958 – ident: ref39 doi: 10.1109/ICASSP.2013.6637745 – ident: ref14 doi: 10.1109/ICASSP.2014.6853676 – start-page: 708 year: 0 ident: ref78 article-title: Electric guitar playing technique detection in real-world recordings based on F0 sequence pattern recognition publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: chen – year: 2014 ident: ref19 publication-title: Sparse modeling theory algorithms and applications doi: 10.1201/b17758 contributor: fullname: rish – ident: ref67 doi: 10.1016/j.sigpro.2005.06.007 – ident: ref40 doi: 10.1109/ICASSP.2015.7178034 – ident: ref41 doi: 10.1109/ICASSP.2013.6637607 – ident: ref47 doi: 10.1109/ICASSP.2012.6289134 – year: 2014 ident: ref55 article-title: Pitch-informed solo and accompaniment separation contributor: fullname: cerón – ident: ref23 doi: 10.1109/TIP.2015.2495260 – ident: ref17 doi: 10.1002/cpa.20132 – year: 0 ident: ref11 article-title: A probabilistic latent variable model for acoustic modeling publication-title: Proc Workshop Adv Models Acoust Process NIPS contributor: fullname: smaragdis – ident: ref45 doi: 10.1109/JSTSP.2011.2159701 – ident: ref69 doi: 10.1137/S1064827596304010 – ident: ref49 doi: 10.1109/ICASSP.2013.6637776 – start-page: 277 year: 0 ident: ref48 article-title: Score-informed leading voice separation from monaural audio publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: joder – start-page: 1065 year: 2007 ident: ref74 article-title: A survey of convolutive blind source separation methods publication-title: Springer Handbook of Speech Processing contributor: fullname: pedersen – year: 2016 ident: ref81 article-title: SParse Optimization Research COde (SPORCO) contributor: fullname: wohlberg – ident: ref77 doi: 10.1109/LSP.2015.2433061 – year: 2010 ident: ref61 article-title: Fast signal reconstruction from magnitude STFT spectrogram based on spectrogram consistency publication-title: Proc 13th Int Conf Digital Audio Effects contributor: fullname: roux – ident: ref7 doi: 10.1109/TASL.2011.2172425 – ident: ref9 doi: 10.1109/ICASSP.2014.6855053 – year: 2011 ident: ref79 – ident: ref5 doi: 10.1109/TASL.2006.885253 – ident: ref26 doi: 10.1109/ICASSP.2015.7177967 – ident: ref46 doi: 10.1109/ICASSP.2012.6287834 – start-page: 559 year: 0 ident: ref38 article-title: A comparison of sound segregation techniques for predominant instrument recognition in musical audio signals publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: bosch – year: 2010 ident: ref83 article-title: BSS_Eval: A toolbox for performance measurement in (blind) source separation – ident: ref76 doi: 10.1109/MSP.2012.2208663 – start-page: 327 year: 0 ident: ref37 article-title: Musical instrument recognition in polyphonic audio using source-filter model for sound separation publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: heittola – ident: ref51 doi: 10.1109/ASPAA.2009.5346542 – start-page: 337 year: 0 ident: ref33 article-title: Separation of vocals from polyphonic audio recordings publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: vembu – year: 2012 ident: ref64 article-title: Phase-based informed source separation for active listening of music publication-title: Proc Int Conf Digital Audio Effects contributor: fullname: sturmel – start-page: 314 year: 0 ident: ref31 article-title: Remixing stereo music with score-informed source separation publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: woodruff – ident: ref56 doi: 10.1109/TASLP.2015.2450494 – volume: 11 start-page: 730 year: 1999 ident: ref65 article-title: Coding time-varying signals using sparse, shift-invariant representations publication-title: Adv Neural Inf Process Syst contributor: fullname: lewicki – ident: ref6 doi: 10.1162/neco.2008.04-08-771 – ident: ref60 doi: 10.1109/TASLP.2014.2362006 – start-page: 369 year: 0 ident: ref13 article-title: Beyond NMF: Time-domain audio source separation without phase reconstruction publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: yoshii – ident: ref59 doi: 10.1109/TASL.2011.2109379 – start-page: 19 year: 0 ident: ref85 article-title: Multiple-instrument polyphonic music transcription using a convolutive probabilistic model publication-title: Proc Sound and Music Computing Conf contributor: fullname: benetos – ident: ref36 doi: 10.1109/LSP.2016.2514845 – ident: ref42 doi: 10.1109/TASL.2007.914120 – ident: ref18 doi: 10.1002/cpa.20124 – ident: ref75 doi: 10.1109/ICIP.2016.7532675 – ident: ref29 doi: 10.1109/TASL.2009.2034186 – ident: ref15 doi: 10.1109/ICASSP.2015.7177937 – volume: 401 start-page: 788 year: 1999 ident: ref57 article-title: Learning the parts of objects by non-negative matrix factorization publication-title: Nature doi: 10.1038/44565 contributor: fullname: lee – start-page: 17 year: 0 ident: ref4 article-title: Investigating single-channel audio source separation methods based on non-negative matrix factorization publication-title: Proc ICA Res Netw Int Workshop contributor: fullname: wang – ident: ref10 doi: 10.1109/ICASSP.2016.7471637 – ident: ref52 doi: 10.1109/ICASSP.2011.5946389 – ident: ref70 doi: 10.1561/2200000016 – volume: 3 start-page: 229 year: 0 ident: ref80 article-title: RWC music database: Music genre database and musical instrument sound database publication-title: Proc Int Soc Music Inf Retrieval Conf contributor: fullname: goto – ident: ref16 doi: 10.1109/MSP.2012.2205029 – year: 2008 ident: ref68 article-title: Shift invariant sparse coding of image and music data contributor: fullname: mørup – start-page: 494 year: 2004 ident: ref84 article-title: Non-negative matrix factor deconvolution; extraction of multiple sound sources from monophonic inputs publication-title: Independent Component Analysis and Blind Signal Separation doi: 10.1007/978-3-540-30110-3_63 contributor: fullname: smaragdis – ident: ref44 doi: 10.1007/s10844-013-0258-3 – ident: ref35 doi: 10.1109/ICASSP.2015.7178063 – ident: ref87 doi: 10.1111/j.1467-9868.2005.00532.x – start-page: 101 year: 0 ident: ref63 article-title: Multiresolution STFT phase estimation with frame-wise posterior window length decision publication-title: Proc Int Conf Digit Audio Effects contributor: fullname: gnann – ident: ref8 doi: 10.1109/ICASSP.2009.4960364 – ident: ref88 doi: 10.1109/MLSP.2015.7324332 – start-page: 509 year: 0 ident: ref2 article-title: Shifted 2D nonnegative tensor factorisation publication-title: Proc IET Irish Signals Syst Conf contributor: fullname: fitzgerald – ident: ref73 doi: 10.1109/LSP.2015.2466447 – ident: ref22 doi: 10.1109/ICASSP.2014.6854992 – volume: 17 start-page: 1361 year: 2009 ident: ref54 article-title: Monaural musical sound separation based on pitch and common amplitude modulation publication-title: IEEE Trans Audio Speech Lang Process doi: 10.1109/TASL.2009.2020886 contributor: fullname: li – ident: ref58 doi: 10.1109/ICASSP.2010.5495699 – ident: ref3 doi: 10.1007/11679363_87 – ident: ref66 doi: 10.1109/TSA.2005.860346 – ident: ref1 doi: 10.1109/ASPAA.2003.1285860 – ident: ref24 doi: 10.1109/CVPR.2013.57 |
SSID | ssj0001079974 |
Score | 2.1446478 |
Snippet | We present a comprehensive performance study of a new time-domain approach for estimating the components of an observed monaural audio mixture. Unlike existing... |
SourceID | osti proquest crossref ieee |
SourceType | Open Access Repository Aggregation Database Publisher |
StartPage | 2158 |
SubjectTerms | Activation Algorithms Approximation Coding Computer Science Convolution Convolutional codes convolutional sparse coding Convolutional sparse coding (CSC) Dictionaries Information Science Instruments Mathematics MATHEMATICS AND COMPUTING Monaural music source separation multipitch estimation (MPE) Music Musical scores non-negative matrix factorization nonnegative matrix factorization (NMF) phase score-informed source separation Separation Sound filters Source separation Time-domain analysis |
Title | Monaural Music Source Separation Using Convolutional Sparse Coding |
URI | https://ieeexplore.ieee.org/document/7533514 https://www.proquest.com/docview/1830921139 https://search.proquest.com/docview/1855384796 https://www.osti.gov/servlets/purl/1495128 |
Volume | 24 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLYGXODAayAKAxWJG3SkXZc0R0AghAAhDaTdojwvSC1iHQd-PU7ajeeBU6skUlM7tj8ntgNwpDQttCto4rJMJ_7gLOGayIQ4ljvFHTUmBMje0-un_GY8HHfgZJ4LY60NwWe271_DWb6p9NRvlZ0itPaB5wuwUJCsydX63E8hjPNQdBkxAk_Q6pNZjgzhp49no9sHH8hF-4j3cRUPvtmhcLEKPioUq19KOViaqzW4m82xCTB57k9r1dfvP8o3_vcn1mG1hZzxWbNGNqBjy01Y-VKIcBOWwnXPXThHEZe-EEccGuJR2NqPR7apEF6VcQgxiC-q8q1dszh2hL0Ti43eDm7B09Xl48V10t6ykGgEJ3WilElzxQ3yEtFTagdKD1OdWpZLkxklpUEI4NzQItko04yk2iFmdAYdn5TJbLANi2VV2h2ImS20pFQiClS5k65IqbZFjk4SK1DBswiOZzQXL00xDRGcEMJF4JDwHBIthyLoeurNR7aEi2DPs0kgQvBlbrWPB9K18J4e2toIejPuiVYaJwLVFuHo6Q54BIfzbpQjfzgiS1tN_Zgh6v6ccbr793f3YNnPrslD7MFi_Tq1-whIanUQVuIH12TcWQ |
link.rule.ids | 230,315,786,790,802,891,27955,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLZ4HIADb0R5FokbdKRblzRHQKABAyFtSNyiPC9ILYKOA78eJ-3G88CpVRKpqR3bnxPbAThUmuba5TRx7bZO_MFZwjWRCXEsc4o7akwIkL2jvYfs-rH7OAXHk1wYa20IPrMt_xrO8k2pR36r7AShtQ88n4ZZtPOE1dlanzsqhHEeyi4jSuAJ2n0yzpIh_GR4Oujf-1Au2kLEj-u4880ShatV8FGiYP1Sy8HWXC7B7XiWdYjJU2tUqZZ-_1HA8b-_sQyLDeiMT-tVsgJTtliFhS-lCFdhNlz4vAZnKOTSl-KIQ0M8CJv78cDWNcLLIg5BBvF5Wbw1qxbHDrD31WKjt4Tr8HB5MTzvJc09C4lGeFIlSpk0U9wgN5Guqe0o3U11alkmTdsoKQ2CAOe6FslGmWYk1Q5RozPo-qRMtjsbMFOUhd2EmNlcS0ol4kCVOenylGqbZ-gmsRxVPIvgaExz8VyX0xDBDSFcBA4JzyHRcCiCNU-9yciGcBFsezYJxAi-0K32EUG6Et7XQ2sbwc6Ye6KRx1eBiotw9HU7PIKDSTdKkj8ekYUtR35MF7V_xjjd-vu7-zDXG972Rf_q7mYb5v1M66zEHZipXkZ2F-FJpfbCqvwAnIPfrQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Monaural+Music+Source+Separation+Using+Convolutional+Sparse+Coding&rft.jtitle=IEEE%2FACM+transactions+on+audio%2C+speech%2C+and+language+processing&rft.au=Jao%2C+Ping-Keng&rft.au=Su%2C+Li&rft.au=Yang%2C+Yi-Hsuan&rft.au=Wohlberg%2C+Brendt&rft.date=2016-11-01&rft.issn=2329-9290&rft.eissn=2329-9304&rft.volume=24&rft.issue=11&rft.spage=2158&rft.epage=2170&rft_id=info:doi/10.1109%2FTASLP.2016.2598323&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2329-9290&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2329-9290&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2329-9290&client=summon |