{"id":"https://openalex.org/W2889992917","doi":"https://doi.org/10.1109/icassp.2018.8461526","title":"Permutation Invariant Training for Speaker-Independent Multi-Pitch Tracking","display_name":"Permutation Invariant Training for Speaker-Independent Multi-Pitch Tracking","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2889992917","doi":"https://doi.org/10.1109/icassp.2018.8461526","mag":"2889992917"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101800003","display_name":"Yuzhou Liu","orcid":"https://orcid.org/0000-0002-7030-9121"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhou Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5594","last_page":"5598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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/speech-recognition","display_name":"Speech recognition","score":0.7356698513031006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6495705842971802},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6381083726882935},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6050969362258911},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5540480017662048},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.530433177947998},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45326539874076843},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4203546643257141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40940871834754944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.388820618391037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35891836881637573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2063518762588501},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.1055682897567749}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7356698513031006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6495705842971802},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6381083726882935},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6050969362258911},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5540480017662048},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.530433177947998},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45326539874076843},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4203546643257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40940871834754944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.388820618391037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35891836881637573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2063518762588501},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.1055682897567749},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1881757884","https://openalex.org/W1904365287","https://openalex.org/W2015143272","https://openalex.org/W2064675550","https://openalex.org/W2065495703","https://openalex.org/W2088361146","https://openalex.org/W2091425152","https://openalex.org/W2102308274","https://openalex.org/W2115129089","https://openalex.org/W2119599673","https://openalex.org/W2143341575","https://openalex.org/W2156387975","https://openalex.org/W2400225965","https://openalex.org/W2583110984","https://openalex.org/W2667576870","https://openalex.org/W2734774145","https://openalex.org/W2964121744","https://openalex.org/W4299729612","https://openalex.org/W6631190155","https://openalex.org/W6639356260","https://openalex.org/W6640036494","https://openalex.org/W6675172360","https://openalex.org/W6682889407","https://openalex.org/W6739505663"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"Speaker-independent":[0],"multi-pitch":[1,35,84],"tracking":[2,54,71],"has":[3],"been":[4,48],"a":[5,16,43],"long-standing":[6],"problem":[7],"in":[8],"speech":[9,38,44,69],"processing.":[10],"In":[11],"this":[12],"study,":[13],"we":[14],"extend":[15],"recurrent":[17],"neural":[18],"network-factorial":[19],"hidden":[20],"Markov":[21],"model":[22],"(RNN-FHMM)":[23],"framework":[24],"and":[25,39,82],"use":[26],"the":[27,61,67],"utterance-level":[28],"permutation":[29],"invariant":[30],"training":[31],"(uPIT)":[32],"criterion":[33],"for":[34,91],"tracking.":[36],"Separated":[37],"label":[40,76],"permutations":[41,77],"from":[42],"separation":[45],"uPIT-RNN":[46],"have":[47],"further":[49],"incorporated":[50],"to":[51],"improve":[52],"pitch":[53],"performance.":[55],"We":[56],"evaluate":[57],"our":[58],"methods":[59],"on":[60],"GRID":[62],"database.":[63],"Results":[64],"indicate":[65],"that":[66],"proposed":[68],"separation-pitch":[70],"system":[72],"with":[73],"matched":[74],"uPIT":[75],"outperforms":[78],"all":[79],"other":[80],"gender-dependent":[81],"speaker-independent":[83],"trackers.":[85],"The":[86],"improvement":[87],"is":[88],"more":[89],"significant":[90],"challenging":[92],"same-gender":[93],"mixtures.":[94]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}