{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:13:24Z","timestamp":1783098804968,"version":"3.54.6"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2982285","type":"journal-article","created":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T20:08:33Z","timestamp":1584734913000},"page":"1118-1128","source":"Crossref","is-referenced-by-count":70,"title":["SPICE: Self-Supervised Pitch Estimation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1321-9015","authenticated-orcid":false,"given":"Beat","family":"Gfeller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1930-5571","authenticated-orcid":false,"given":"Christian","family":"Frank","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2155-450X","authenticated-orcid":false,"given":"Dominik","family":"Roblek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0316-3281","authenticated-orcid":false,"given":"Matt","family":"Sharifi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7682-6795","authenticated-orcid":false,"given":"Marco","family":"Tagliasacchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5588-6828","authenticated-orcid":false,"given":"Mihajlo","family":"Velimirovic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.1999.810857"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","article-title":"Self-supervised audio representation learning for mobile devices","author":"tagliasacchi","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00840"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref35","article-title":"UnsuperPoint: End-to-end unsupervised interest point detector and descriptor","author":"christiansen","year":"2019"},{"key":"ref34","article-title":"Unsupervised feature learning for audio analysis","author":"meyer","year":"0","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"537","DOI":"10.21437\/Interspeech.2005-335","article-title":"Nearly defect-free F0 trajectory extraction for expressive speech modifications based on STRAIGHT","author":"kawahara","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2042119"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2188515"},{"key":"ref13","first-page":"71","article-title":"An analysis\/synthesis framework for automatic f0 annotation of multitrack datasets","author":"salamon","year":"0","journal-title":"Proc Int Soc for Music Inf Retrieval Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5709\/acp-0152-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2326991"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1109\/TASL.2009.2026503","article-title":"On the improvement of singing voice separation for monaural recordings using the MIR-1K dataset","volume":"18","author":"jang","year":"2010","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171720"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081482"},{"key":"ref28","article-title":"Multitask learning for fundamental frequency estimation in music","author":"bittner","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162765"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref3","first-page":"1","article-title":"Barberpole phasing and flanging illusions","author":"esqueda","year":"0","journal-title":"Proc 5th Int Conf Digital Audio Effects (DAFx)"},{"key":"ref6","first-page":"495","article-title":"A robust algorithm for pitch tracking (RAPT)","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref5","first-page":"97","article-title":"Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound","author":"boersma","year":"1993","journal-title":"IFA Proceedings 17"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.2951592"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/9781139051699"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325920"},{"key":"ref1","first-page":"612","article-title":"Deep convolutional networks on the pitch spiral for music instrument recognition","author":"lostanlen","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-240"},{"key":"ref22","first-page":"266","article-title":"Comparison of pitch trackers for real-time guitar effects","author":"von dem knesebeck","year":"0","journal-title":"Proc Digital Audio Effects (DAFx)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639185"},{"key":"ref42","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"706","article-title":"Noise robust pitch tracking by subband autocorrelation classification","volume":"1","author":"lee","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref41","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2363410"},{"key":"ref26","first-page":"46","article-title":"Unsupervised classification of voiced speech and pitch tracking using forward-backward Kalman filtering","author":"b\u00f6nninghoff","year":"2016","journal-title":"Proc 12 ITG Symp Speech Commun"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00171"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953229"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09043478.pdf?arnumber=9043478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T10:58:58Z","timestamp":1666177138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9043478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2982285","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}