{"id":"https://openalex.org/W4372260108","doi":"https://doi.org/10.1109/icassp49357.2023.10095919","title":"Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism","display_name":"Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260108","doi":"https://doi.org/10.1109/icassp49357.2023.10095919"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095919","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5086910479","display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002887879","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0002-9774-3657"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038041333","display_name":"Keiichi Tokuda","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9976999759674072,"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/naturalness","display_name":"Naturalness","score":0.817217230796814},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8140057325363159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7915223836898804},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7787352800369263},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6396358013153076},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.4796048402786255},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47692033648490906},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.431831032037735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3635270595550537},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11367741227149963}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.817217230796814},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8140057325363159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915223836898804},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7787352800369263},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6396358013153076},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.4796048402786255},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47692033648490906},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.431831032037735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3635270595550537},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11367741227149963},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095919","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W2106792148","https://openalex.org/W2133564696","https://openalex.org/W2471520273","https://openalex.org/W2767052532","https://openalex.org/W2886769154","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2940405045","https://openalex.org/W2962883485","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972702018","https://openalex.org/W2972746749","https://openalex.org/W2972910332","https://openalex.org/W2973046048","https://openalex.org/W3015437531","https://openalex.org/W3015499232","https://openalex.org/W3033411150","https://openalex.org/W3082910224","https://openalex.org/W3091928890","https://openalex.org/W3095074555","https://openalex.org/W3096437652","https://openalex.org/W3097514409","https://openalex.org/W3133525064","https://openalex.org/W3160427568","https://openalex.org/W3161296985","https://openalex.org/W3187128306","https://openalex.org/W3190244907","https://openalex.org/W3204728450","https://openalex.org/W4298397573","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6736996214","https://openalex.org/W6756197946","https://openalex.org/W6763783096","https://openalex.org/W6767906187","https://openalex.org/W6778823374","https://openalex.org/W6783382068","https://openalex.org/W6784545093"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W2111961547"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,9],"novel":[4],"sequence-to-sequence":[5],"(seq2seq)":[6],"model":[7,53,126],"with":[8,50,74],"musical":[10,103],"note":[11],"position-aware":[12],"attention":[13,76,87,94],"mechanism":[14,88],"for":[15],"singing":[16,44,118],"voice":[17],"synthesis":[18],"(SVS).":[19],"A":[20],"seq2seq":[21,72],"modeling":[22,31,42,70,114],"approach":[23],"that":[24,123],"can":[25],"simultaneously":[26],"perform":[27,68],"acoustic":[28],"and":[29,134],"temporal":[30,41,83],"is":[32,89,127],"attractive.":[33],"However,":[34],"due":[35],"to":[36,91,111],"the":[37,40,93,98,102,113,117,124],"difficulty":[38],"of":[39,43,116,131,136],"voices,":[45],"many":[46],"recent":[47],"SVS":[48],"systems":[49],"an":[51,75],"encoder-decoder-based":[52],"still":[54],"rely":[55],"on":[56,58],"explicitly":[57],"duration":[59],"information":[60],"generated":[61],"by":[62,96,101],"additional":[63],"modules.":[64],"Although":[65],"some":[66],"studies":[67],"simultaneous":[69],"using":[71],"models":[73],"mechanism,":[77],"they":[78],"have":[79],"insufficient":[80],"robustness":[81,135],"against":[82],"modeling.":[84],"The":[85],"proposed":[86,125],"designed":[90],"estimate":[92],"weights":[95],"considering":[97],"rhythm":[99],"given":[100],"score.":[104],"Furthermore,":[105],"several":[106],"techniques":[107],"are":[108],"also":[109],"introduced":[110],"improve":[112],"performance":[115],"voice.":[119],"Experimental":[120],"results":[121],"indicated":[122],"effective":[128],"in":[129],"terms":[130],"both":[132],"naturalness":[133],"timing.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
