{"id":"https://openalex.org/W3011176162","doi":"https://doi.org/10.1109/taslp.2020.2982285","title":"SPICE: Self-Supervised Pitch Estimation","display_name":"SPICE: Self-Supervised Pitch Estimation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3011176162","doi":"https://doi.org/10.1109/taslp.2020.2982285","mag":"3011176162"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2982285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2982285","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09043478.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09043478.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Beat Gfeller","orcid":"https://orcid.org/0000-0002-1321-9015"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Beat Gfeller","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1321-9015","affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christian Frank","orcid":"https://orcid.org/0000-0002-1930-5571"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christian Frank","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1930-5571","affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dominik Roblek","orcid":"https://orcid.org/0000-0002-2155-450X"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dominik Roblek","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-2155-450X","affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Matt Sharifi","orcid":"https://orcid.org/0000-0002-0316-3281"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matt Sharifi","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-0316-3281","affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marco Tagliasacchi","orcid":"https://orcid.org/0000-0002-7682-6795"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Tagliasacchi","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7682-6795","affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mihajlo Velimirovic","orcid":"https://orcid.org/0000-0002-5588-6828"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mihajlo Velimirovic","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5588-6828","affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210100430"],"apc_list":null,"apc_paid":null,"fwci":4.4896,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.95228018,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"1118","last_page":"1128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.49900001287460327,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.49900001287460327,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4291999936103821,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.02419999986886978,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5580000281333923},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4950000047683716},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44670000672340393},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.384799987077713},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.384799987077713},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3650999963283539},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.36309999227523804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5924999713897705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5633000135421753},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5580000281333923},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4788999855518341},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3650999963283539},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.36309999227523804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32679998874664307},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2824000120162964},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2678999900817871}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.2982285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2982285","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09043478.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1910.11664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11664","pdf_url":"https://arxiv.org/pdf/1910.11664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/taslp.2020.2982285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2982285","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09043478.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3011176162.pdf","grobid_xml":"https://content.openalex.org/works/W3011176162.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W198589515","https://openalex.org/W1791774586","https://openalex.org/W1975079546","https://openalex.org/W1976069042","https://openalex.org/W2034300186","https://openalex.org/W2034995162","https://openalex.org/W2046033161","https://openalex.org/W2091425152","https://openalex.org/W2093231248","https://openalex.org/W2097423688","https://openalex.org/W2107328928","https://openalex.org/W2108771579","https://openalex.org/W2118774185","https://openalex.org/W2124539664","https://openalex.org/W2161632835","https://openalex.org/W2166348079","https://openalex.org/W2191779130","https://openalex.org/W2321533354","https://openalex.org/W2518618011","https://openalex.org/W2603256597","https://openalex.org/W2612464443","https://openalex.org/W2621177543","https://openalex.org/W2755000466","https://openalex.org/W2767754137","https://openalex.org/W2799087757","https://openalex.org/W2962866891","https://openalex.org/W2964217527","https://openalex.org/W4232595861","https://openalex.org/W6631190155","https://openalex.org/W6676245417","https://openalex.org/W6679739227","https://openalex.org/W6697040288","https://openalex.org/W6736723571","https://openalex.org/W6746570019","https://openalex.org/W6746960179","https://openalex.org/W6754881664","https://openalex.org/W6765499649","https://openalex.org/W6766016090","https://openalex.org/W6840487619","https://openalex.org/W6844194202","https://openalex.org/W6922646544"],"related_works":[],"abstract_inverted_index":{"We":[0,18,85],"propose":[1,41],"a":[2,35,44,68,87,123,165],"model":[3,125],"to":[4,14,42,51,67,98,113,135,145,161,170,187],"estimate":[5,52,162],"the":[6,20,28,72,78,81,96,99,106,109,114,130,137,140,156],"fundamental":[7],"frequency":[8,32],"in":[9,108,117],"monophonic":[10],"audio,":[11],"often":[12],"referred":[13],"as":[15,144],"pitch":[16,53,64,141,163],"estimation.":[17],"acknowledge":[19],"fact":[21],"that":[22,63,105,155],"obtaining":[23],"ground":[24],"truth":[25],"annotations":[26],"at":[27,164],"required":[29],"temporal":[30],"and":[31,103,149,177],"resolution":[33],"is":[34,49,62,75,111,133,159],"particularly":[36],"daunting":[37],"task.":[38],"Therefore,":[39],"we":[40,121],"adopt":[43],"self-supervised":[45,88],"learning":[46],"technique,":[47],"which":[48,132],"able":[50,134,160],"without":[54],"any":[55],"form":[56],"of":[57,80,95,129,139,167],"supervision.":[58],"The":[59],"key":[60],"observation":[61],"shift":[65],"maps":[66],"simple":[69],"translation":[70],"when":[71],"audio":[73,179],"signal":[74],"analysed":[76],"through":[77],"lens":[79],"constant-Q":[82],"transform":[83],"(CQT).":[84],"design":[86],"task":[89],"by":[90],"feeding":[91],"two":[92],"shifted":[93],"slices":[94],"CQT":[97],"same":[100],"convolutional":[101],"encoder,":[102,131],"require":[104,185],"difference":[107,116],"outputs":[110],"proportional":[112],"corresponding":[115],"pitch.":[118],"In":[119],"addition,":[120],"introduce":[122],"small":[124],"head":[126],"on":[127,175],"top":[128],"determine":[136],"confidence":[138],"estimate,":[142],"so":[143],"distinguish":[146],"between":[147],"voiced":[148],"unvoiced":[150],"audio.":[151],"Our":[152],"results":[153],"show":[154],"proposed":[157],"method":[158],"level":[166],"accuracy":[168],"comparable":[169],"fully":[171],"supervised":[172],"models,":[173],"both":[174],"clean":[176],"noisy":[178],"samples,":[180],"although":[181],"it":[182],"does":[183],"not":[184],"access":[186],"large":[188],"labeled":[189],"datasets.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-03-23T00:00:00"}