{"id":"https://openalex.org/W3160427568","doi":"https://doi.org/10.1109/icassp39728.2021.9414348","title":"Sequence-To-Sequence Singing Voice Synthesis With Perceptual Entropy Loss","display_name":"Sequence-To-Sequence Singing Voice Synthesis With Perceptual Entropy Loss","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160427568","doi":"https://doi.org/10.1109/icassp39728.2021.9414348","mag":"3160427568"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114706275","display_name":"Shuai Guo","orcid":"https://orcid.org/0009-0003-9705-6464"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Guo","raw_affiliation_strings":["Renmin University of China, P. R. China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, P. R. China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071652041","display_name":"Nan Huo","orcid":"https://orcid.org/0000-0002-9305-3309"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Huo","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074415592","display_name":"Yuekai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuekai Zhang","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, P. R. China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, P. R. China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008336983"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.3147,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88931272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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":0.9983999729156494,"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/singing","display_name":"Singing","score":0.8590047955513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7391270399093628},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6064945459365845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5867400169372559},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.57347571849823},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5509042143821716},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5233204364776611},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4844803512096405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4024820327758789},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07969805598258972},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07960274815559387},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07159468531608582}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8590047955513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391270399093628},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6064945459365845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5867400169372559},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.57347571849823},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5509042143821716},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5233204364776611},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4844803512096405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4024820327758789},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07969805598258972},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07960274815559387},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07159468531608582},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W1525613233","https://openalex.org/W2058097301","https://openalex.org/W2096588881","https://openalex.org/W2124097505","https://openalex.org/W2128301448","https://openalex.org/W2144520790","https://openalex.org/W2408435475","https://openalex.org/W2515336442","https://openalex.org/W2516406502","https://openalex.org/W2567070169","https://openalex.org/W2778460379","https://openalex.org/W2889244839","https://openalex.org/W2921576841","https://openalex.org/W2937242376","https://openalex.org/W2940405045","https://openalex.org/W2963403868","https://openalex.org/W2963970792","https://openalex.org/W2984106626","https://openalex.org/W2995005087","https://openalex.org/W2995670387","https://openalex.org/W3015437531","https://openalex.org/W3015499232","https://openalex.org/W3015516707","https://openalex.org/W3015645837","https://openalex.org/W3019084079","https://openalex.org/W3025165719","https://openalex.org/W3035430139","https://openalex.org/W3048084370","https://openalex.org/W3048092838","https://openalex.org/W3081279708","https://openalex.org/W3082910224","https://openalex.org/W3096437652","https://openalex.org/W3097152652","https://openalex.org/W3097514409","https://openalex.org/W3097777922","https://openalex.org/W3097797284","https://openalex.org/W3114301328","https://openalex.org/W3133525064","https://openalex.org/W4235133917","https://openalex.org/W4385245566","https://openalex.org/W6601203246","https://openalex.org/W6631229253","https://openalex.org/W6678318511","https://openalex.org/W6731370813","https://openalex.org/W6739901393","https://openalex.org/W6761725420","https://openalex.org/W6771539914","https://openalex.org/W6771665576","https://openalex.org/W6772134836","https://openalex.org/W6776400185","https://openalex.org/W6783382068"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"The":[0],"neural":[1],"network":[2],"(NN)":[3],"based":[4],"singing":[5,69,109],"voice":[6,70],"synthesis":[7],"(SVS)":[8],"systems":[9,36],"require":[10],"sufficient":[11],"data":[12,24,30,40],"to":[13,20,23,61],"train":[14],"well":[15],"and":[16,42,89,104,114],"are":[17,18],"prone":[19],"over-fitting":[21,102],"due":[22],"scarcity.":[25],"However,":[26],"we":[27,48,72],"often":[28],"encounter":[29],"limitation":[31],"problem":[32,103],"in":[33,112],"building":[34],"SVS":[35],"because":[37],"of":[38,76],"high":[39],"acquisition":[41],"annotation":[43],"cost,.":[44],"In":[45],"this":[46],"work,":[47],"propose":[49],"a":[50,57,66],"Perceptual":[51],"Entropy":[52],"(PE)":[53],"loss":[54,79,98],"derived":[55],"from":[56],"psycho-acoustic":[58],"hearing":[59],"model":[60],"regularize":[62],"the":[63,74,77,86,96,101,107],"network.":[64],"With":[65],"one-hour":[67],"open-source":[68],"database,":[71],"explore":[73],"impact":[75],"PE":[78,97],"on":[80],"various":[81],"main-stream":[82],"sequence-to-sequence":[83],"models,":[84],"including":[85],"RNN-based,":[87],"transformer-based,":[88],"conformer-based":[90],"models.":[91],"Our":[92],"experiments":[93],"show":[94],"that":[95],"can":[99],"mitigate":[100],"significantly":[105],"improve":[106],"synthesized":[108],"quality":[110],"reflected":[111],"objective":[113],"subjective":[115],"evaluations.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}