Score guided audio restoration via generalised coupled tensor factorisation
Generalised coupled tensor factorisation is a recently proposed algorithmic framework for simultaneously estimating tensor factorisation models where several observed tensors can share a set of latent factors. This paper proposes a model in this framework for coupled factorisation of piano spectrogr...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Tagungsbericht |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 5372 |
---|---|
container_issue | |
container_start_page | 5369 |
container_title | |
container_volume | |
creator | Simsekli, U. Yilmaz, Y. K. Cemgil, A. T. |
description | Generalised coupled tensor factorisation is a recently proposed algorithmic framework for simultaneously estimating tensor factorisation models where several observed tensors can share a set of latent factors. This paper proposes a model in this framework for coupled factorisation of piano spectrograms and piano roll representations to solve audio interpolation and restoration problem. The model incorporates temporal and harmonic information from an approximate musical score (not necessarily belonging to the played piece), and spectral information from isolated piano sounds. The performance of the proposed approach is evaluated on the restoration of classical music pieces where we get about 5dB SNR improvement when 50% of data frames are missing. |
doi_str_mv | 10.1109/ICASSP.2012.6289134 |
format | Conference Proceeding |
fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6289134</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6289134</ieee_id><sourcerecordid>6289134</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-687f2907e3ec2c8c1927138221fee054d196bbe7e78526c93fc1098372135073</originalsourceid><addsrcrecordid>eNo1kM1OwzAQhM2fRCh5gl78AgleO_HPEVVQEJVASg_cKtfZVEYhqewEibfHgrKXOew3I80QsgRWAjBz97y6b5q3kjPgpeTagKjOSG6UhkoqwVglzTnJuFCmAMPeL8jN_6OuLkkGNWeFhMpckzzGD5YuWZmQGXlp3BiQHmbfYkvt3PqRBozTGOzkx4F-eUsPOGCwvY-JcON87JNOOMQx0M66hPr4C9-Sq872EfOTLsj28WG7eio2r-vUYFN4UPVUSK06bphCgY477cBwBUJzDh0iq6sWjNzvUaHSNZfOiM6lDbRQHETNlFiQ5V-sR8TdMfhPG753p1nED9FJUkk</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Score guided audio restoration via generalised coupled tensor factorisation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Simsekli, U. ; Yilmaz, Y. K. ; Cemgil, A. T.</creator><creatorcontrib>Simsekli, U. ; Yilmaz, Y. K. ; Cemgil, A. T.</creatorcontrib><description>Generalised coupled tensor factorisation is a recently proposed algorithmic framework for simultaneously estimating tensor factorisation models where several observed tensors can share a set of latent factors. This paper proposes a model in this framework for coupled factorisation of piano spectrograms and piano roll representations to solve audio interpolation and restoration problem. The model incorporates temporal and harmonic information from an approximate musical score (not necessarily belonging to the played piece), and spectral information from isolated piano sounds. The performance of the proposed approach is evaluated on the restoration of classical music pieces where we get about 5dB SNR improvement when 50% of data frames are missing.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 1467300454</identifier><identifier>ISBN: 9781467300452</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 9781467300469</identifier><identifier>EISBN: 1467300446</identifier><identifier>EISBN: 9781467300445</identifier><identifier>EISBN: 1467300462</identifier><identifier>DOI: 10.1109/ICASSP.2012.6289134</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustic noise ; Audio Restoration ; Computational modeling ; Cost function ; Coupled Tensor Factorisation ; Equations ; Mathematical model ; Signal to noise ratio ; Tensile stress</subject><ispartof>2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, p.5369-5372</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6289134$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6289134$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Simsekli, U.</creatorcontrib><creatorcontrib>Yilmaz, Y. K.</creatorcontrib><creatorcontrib>Cemgil, A. T.</creatorcontrib><title>Score guided audio restoration via generalised coupled tensor factorisation</title><title>2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</title><addtitle>ICASSP</addtitle><description>Generalised coupled tensor factorisation is a recently proposed algorithmic framework for simultaneously estimating tensor factorisation models where several observed tensors can share a set of latent factors. This paper proposes a model in this framework for coupled factorisation of piano spectrograms and piano roll representations to solve audio interpolation and restoration problem. The model incorporates temporal and harmonic information from an approximate musical score (not necessarily belonging to the played piece), and spectral information from isolated piano sounds. The performance of the proposed approach is evaluated on the restoration of classical music pieces where we get about 5dB SNR improvement when 50% of data frames are missing.</description><subject>Acoustic noise</subject><subject>Audio Restoration</subject><subject>Computational modeling</subject><subject>Cost function</subject><subject>Coupled Tensor Factorisation</subject><subject>Equations</subject><subject>Mathematical model</subject><subject>Signal to noise ratio</subject><subject>Tensile stress</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>1467300454</isbn><isbn>9781467300452</isbn><isbn>9781467300469</isbn><isbn>1467300446</isbn><isbn>9781467300445</isbn><isbn>1467300462</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kM1OwzAQhM2fRCh5gl78AgleO_HPEVVQEJVASg_cKtfZVEYhqewEibfHgrKXOew3I80QsgRWAjBz97y6b5q3kjPgpeTagKjOSG6UhkoqwVglzTnJuFCmAMPeL8jN_6OuLkkGNWeFhMpckzzGD5YuWZmQGXlp3BiQHmbfYkvt3PqRBozTGOzkx4F-eUsPOGCwvY-JcON87JNOOMQx0M66hPr4C9-Sq872EfOTLsj28WG7eio2r-vUYFN4UPVUSK06bphCgY477cBwBUJzDh0iq6sWjNzvUaHSNZfOiM6lDbRQHETNlFiQ5V-sR8TdMfhPG753p1nED9FJUkk</recordid><startdate>201203</startdate><enddate>201203</enddate><creator>Simsekli, U.</creator><creator>Yilmaz, Y. K.</creator><creator>Cemgil, A. T.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201203</creationdate><title>Score guided audio restoration via generalised coupled tensor factorisation</title><author>Simsekli, U. ; Yilmaz, Y. K. ; Cemgil, A. T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-687f2907e3ec2c8c1927138221fee054d196bbe7e78526c93fc1098372135073</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Acoustic noise</topic><topic>Audio Restoration</topic><topic>Computational modeling</topic><topic>Cost function</topic><topic>Coupled Tensor Factorisation</topic><topic>Equations</topic><topic>Mathematical model</topic><topic>Signal to noise ratio</topic><topic>Tensile stress</topic><toplevel>online_resources</toplevel><creatorcontrib>Simsekli, U.</creatorcontrib><creatorcontrib>Yilmaz, Y. K.</creatorcontrib><creatorcontrib>Cemgil, A. T.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Simsekli, U.</au><au>Yilmaz, Y. K.</au><au>Cemgil, A. T.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Score guided audio restoration via generalised coupled tensor factorisation</atitle><btitle>2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</btitle><stitle>ICASSP</stitle><date>2012-03</date><risdate>2012</risdate><spage>5369</spage><epage>5372</epage><pages>5369-5372</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>1467300454</isbn><isbn>9781467300452</isbn><eisbn>9781467300469</eisbn><eisbn>1467300446</eisbn><eisbn>9781467300445</eisbn><eisbn>1467300462</eisbn><abstract>Generalised coupled tensor factorisation is a recently proposed algorithmic framework for simultaneously estimating tensor factorisation models where several observed tensors can share a set of latent factors. This paper proposes a model in this framework for coupled factorisation of piano spectrograms and piano roll representations to solve audio interpolation and restoration problem. The model incorporates temporal and harmonic information from an approximate musical score (not necessarily belonging to the played piece), and spectral information from isolated piano sounds. The performance of the proposed approach is evaluated on the restoration of classical music pieces where we get about 5dB SNR improvement when 50% of data frames are missing.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2012.6289134</doi><tpages>4</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1520-6149 |
ispartof | 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, p.5369-5372 |
issn | 1520-6149 2379-190X |
language | eng |
recordid | cdi_ieee_primary_6289134 |
source | IEEE Electronic Library (IEL) Conference Proceedings |
subjects | Acoustic noise Audio Restoration Computational modeling Cost function Coupled Tensor Factorisation Equations Mathematical model Signal to noise ratio Tensile stress |
title | Score guided audio restoration via generalised coupled tensor factorisation |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T03%3A56%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Score%20guided%20audio%20restoration%20via%20generalised%20coupled%20tensor%20factorisation&rft.btitle=2012%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing%20(ICASSP)&rft.au=Simsekli,%20U.&rft.date=2012-03&rft.spage=5369&rft.epage=5372&rft.pages=5369-5372&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=1467300454&rft.isbn_list=9781467300452&rft_id=info:doi/10.1109/ICASSP.2012.6289134&rft_dat=%3Cieee_6IE%3E6289134%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467300469&rft.eisbn_list=1467300446&rft.eisbn_list=9781467300445&rft.eisbn_list=1467300462&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6289134&rfr_iscdi=true |