{"id":"https://openalex.org/W6892336798","doi":"https://doi.org/10.5281/zenodo.10265343","title":"PESTO: Pitch Estimation With Self-Supervised Transposition-Equivariant Objective","display_name":"PESTO: Pitch Estimation With Self-Supervised Transposition-Equivariant Objective","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6892336798","doi":"https://doi.org/10.5281/zenodo.10265343"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265343","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265343","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alain Riou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alain Riou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Stefan Lattner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ga\u00ebtan Hadjeres","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ga\u00ebtan Hadjeres","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Geoffroy Peeters","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9365000128746033,"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":0.9365000128746033,"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":0.024900000542402267,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.012900000438094139,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5699999928474426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.521399974822998},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.41040000319480896},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4077000021934509},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3781999945640564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3368000090122223},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.32760000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692799985408783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5796999931335449},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5699999928474426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3781999945640564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C153405242","wikidata":"https://www.wikidata.org/wiki/Q118819","display_name":"Pitch (Music)","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2888000011444092},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C147710293","wikidata":"https://www.wikidata.org/wiki/Q849428","display_name":"Toeplitz matrix","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265343","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265343","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265343","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265343","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"score":0.4214455783367157,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,152],"this":[1],"paper,":[2],"we":[3,17,82,94],"address":[4],"the":[5,64,74,96,114,161],"problem":[6],"of":[7,63,98,117],"pitch":[8,22,31,91,123,170],"estimation":[9,32,124],"using":[10],"self-supervised":[11,157,165],"learning":[12],"(SSL).":[13],"The":[14],"SSL":[15],"paradigm":[16],"use":[18,46],"is":[19,130],"equivariance":[20],"to":[21,28,101,132],"transposition,":[23],"which":[24,89],"enables":[25],"our":[26,99,111,128,154],"model":[27,75,112,129],"accurately":[29],"perform":[30],"on":[33,40],"monophonic":[34],"audio":[35,66],"after":[36],"being":[37,139],"trained":[38],"only":[39],"a":[41,47,84],"small":[42],"unlabeled":[43],"dataset.":[44],"We":[45,109],"lightweight":[48],"(<":[49],"30k":[50],"parameters)":[51],"Siamese":[52],"neural":[53],"network":[54,100],"that":[55,127],"takes":[56],"as":[57],"inputs":[58],"two":[59,115],"different":[60],"pitch-shifted":[61],"versions":[62],"same":[65],"represented":[67],"by":[68,104],"its":[69],"constant-Q":[70],"transform.":[71],"To":[72],"prevent":[73],"from":[76],"collapsing":[77],"in":[78],"an":[79],"encoder-only":[80],"setting,":[81],"propose":[83],"novel":[85],"class-based":[86],"transposition-equivariant":[87],"objective":[88],"captures":[90],"information.":[92],"Furthermore,":[93],"design":[95],"architecture":[97],"be":[102],"transposition-preserving":[103],"introducing":[105],"learnable":[106],"Toeplitz":[107],"matrices.":[108],"evaluate":[110],"for":[113,149,169],"tasks":[116,135],"singing":[118],"voice":[119],"and":[120,125,136,147,159,166],"musical":[121],"instrument":[122],"show":[126],"able":[131],"generalize":[133],"across":[134],"datasets":[137],"while":[138],"lightweight,":[140],"hence":[141],"remaining":[142],"compatible":[143],"with":[144],"low-resource":[145],"devices":[146],"suitable":[148],"real-time":[150],"applications.":[151],"particular,":[153],"results":[155],"surpass":[156],"baselines":[158],"narrow":[160],"performance":[162],"gap":[163],"between":[164],"supervised":[167],"methods":[168],"estimation.":[171]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}