{"id":"https://openalex.org/W4405633295","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800481","title":"Multi-Resolution Singing Voice Separation","display_name":"Multi-Resolution Singing Voice Separation","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633295","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800481"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5063025053","display_name":"Yih-Liang Shen","orcid":"https://orcid.org/0000-0003-4789-6695"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yih-Liang Shen","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Institute of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Institute of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021033913","display_name":"Ya-Ching Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ya-Ching Lai","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Institute of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Institute of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Institute of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Institute of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2437861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9765999913215637,"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":0.9765999913215637,"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":0.9693999886512756,"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/singing","display_name":"Singing","score":0.7305015325546265},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6727754473686218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6546142101287842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5143312215805054},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4903531074523926},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25525084137916565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24900007247924805},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05722677707672119},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.05638566613197327}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7305015325546265},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6727754473686218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546142101287842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5143312215805054},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4903531074523926},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25525084137916565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24900007247924805},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05722677707672119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05638566613197327}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":22,"referenced_works":["https://openalex.org/W133022121","https://openalex.org/W1496920063","https://openalex.org/W1570504315","https://openalex.org/W1971243715","https://openalex.org/W2054139811","https://openalex.org/W2057745663","https://openalex.org/W2070857950","https://openalex.org/W2073347336","https://openalex.org/W2127851351","https://openalex.org/W2162514423","https://openalex.org/W2516392987","https://openalex.org/W2916985722","https://openalex.org/W2938109705","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963045393","https://openalex.org/W2972411915","https://openalex.org/W2997938083","https://openalex.org/W3015832727","https://openalex.org/W4224936432","https://openalex.org/W4372271367","https://openalex.org/W4375869466"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"It":[0],"has":[1],"been":[2],"shown":[3],"that":[4,45,86],"time-domain":[5,23],"neural":[6],"networks":[7,12],"achieve":[8],"higher":[9],"performance":[10,91],"than":[11],"working":[13],"on":[14,79],"the":[15,37,50,55,74,87,99,108],"short-time":[16],"Fourier":[17],"transform":[18],"(STFT)":[19],"domain.":[20],"The":[21,83],"fully-convolutional":[22],"audio":[24],"separation":[25,31,110],"network":[26],"(Conv-TasNet)":[27],"is":[28],"an":[29],"end-to-end":[30],"model":[32,76],"with":[33,77],"outstanding":[34],"performance.":[35],"However,":[36],"fixed":[38],"convolution":[39],"kernel":[40,56],"length":[41],"in":[42],"Conv-TasNet":[43,78],"implies":[44],"it":[46],"analyzes":[47,66],"signals":[48],"using":[49,68],"frequency":[51,70],"resolution":[52],"constrained":[53],"by":[54],"length.":[57],"This":[58],"paper":[59],"proposes":[60],"a":[61],"multi-frequency-resolution":[62],"(MF)":[63],"architecture,":[64],"which":[65],"sig-nals":[67],"more":[69],"resolutions,":[71],"and":[72],"compares":[73],"MF":[75,88,100],"singing":[80],"voice":[81],"separation.":[82],"results":[84],"show":[85],"architecture":[89,101],"improves":[90],"of":[92],"Conv-TasNet.":[93],"In":[94],"addition,":[95],"we":[96],"also":[97],"demonstrate":[98],"does":[102],"not":[103],"provide":[104],"consistent":[105],"benefits":[106],"to":[107],"STFT-domain":[109],"model.":[111]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}