{"id":"https://openalex.org/W4402979755","doi":"https://doi.org/10.1109/icme57554.2024.10687517","title":"Cycle Frequency-Harmonic-Time Transformer for Note-Level Singing Voice Transcription","display_name":"Cycle Frequency-Harmonic-Time Transformer for Note-Level Singing Voice Transcription","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979755","doi":"https://doi.org/10.1109/icme57554.2024.10687517"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687517","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5043561002","display_name":"Yulun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yulun Wu","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063427144","display_name":"Yaolong Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaolong Ju","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103134236","display_name":"Simon Lui","orcid":"https://orcid.org/0000-0002-0829-2867"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simon Lui","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378741","display_name":"H. J. Yang","orcid":"https://orcid.org/0009-0004-8274-9863"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107911728","display_name":"Fan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Fan","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016213666","display_name":"Xuhao Du","orcid":"https://orcid.org/0000-0003-3035-2309"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhao Du","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043561002"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67324183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9833999872207642,"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":0.9833999872207642,"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":0.9833999872207642,"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":0.9395999908447266,"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/transformer","display_name":"Transformer","score":0.6560137867927551},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6326873898506165},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5521281957626343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.52430260181427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5167714357376099},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.38413912057876587},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.31308987736701965},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.25045186281204224},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17685115337371826},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1557196080684662},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06709063053131104}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6560137867927551},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6326873898506165},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5521281957626343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.52430260181427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5167714357376099},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.38413912057876587},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.31308987736701965},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.25045186281204224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17685115337371826},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1557196080684662},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06709063053131104},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687517","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W86310152","https://openalex.org/W2118774185","https://openalex.org/W2906214917","https://openalex.org/W3158762648","https://openalex.org/W3160649916","https://openalex.org/W4221159539","https://openalex.org/W4225281045","https://openalex.org/W4226106344","https://openalex.org/W4311167650","https://openalex.org/W4311187172","https://openalex.org/W4372260250","https://openalex.org/W4372260308","https://openalex.org/W4372349499","https://openalex.org/W4385245566","https://openalex.org/W4386159990","https://openalex.org/W6601523149","https://openalex.org/W6614159250","https://openalex.org/W6714030504","https://openalex.org/W6733426572","https://openalex.org/W6746836464","https://openalex.org/W6803003856","https://openalex.org/W6811157148","https://openalex.org/W6846575651","https://openalex.org/W6851857987","https://openalex.org/W6967456180"],"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/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Singing":[0],"voice":[1,10],"transcription":[2],"(SVT)":[3],"is":[4],"the":[5,21,25,28,55,75,81],"task":[6],"of":[7,58,104],"converting":[8],"singing":[9,33,59],"music":[11],"into":[12,80],"symbolic":[13],"note":[14],"series.":[15],"Although":[16],"most":[17],"SVT":[18],"models":[19],"utilized":[20,38],"time-frequency":[22],"information":[23,31],"from":[24],"input":[26],"spectrogram,":[27],"useful":[29],"harmonic":[30,56,76],"in":[32],"voices":[34],"has":[35],"not":[36],"been":[37],"enough.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,62],"propose":[44],"a":[45,65,85],"novel":[46],"3D":[47],"Cycle":[48],"Frequency-Harmonic-Time":[49],"Transformer":[50],"(CFT)":[51],"to":[52],"explicitly":[53],"capture":[54],"series":[57],"voices,":[60],"where":[61],"first":[63],"define":[64],"tokenization":[66],"scheme":[67],"that":[68,90],"captures":[69],"harmonics":[70],"across":[71],"multiple":[72],"octaves,":[73],"then":[74],"features":[77],"are":[78],"aggregated":[79],"frequency-harmonic-time":[82],"representations":[83],"via":[84],"cyclic":[86],"architecture.":[87],"Results":[88],"show":[89],"our":[91],"method":[92],"achieves":[93],"state-of-the-art":[94],"performances":[95],"on":[96],"several":[97],"public":[98],"datasets,":[99],"including":[100],"note-wise":[101],"accuracy":[102],"increases":[103],"5.76%":[105],"for":[106,110],"MIR-ST500":[107],"and":[108],"13.56%":[109],"Cmedia.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}