{"id":"https://openalex.org/W4405633843","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800743","title":"Improving Real-Time Music Accompaniment Separation with MMDenseNet","display_name":"Improving Real-Time Music Accompaniment Separation with MMDenseNet","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633843","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800743"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800743","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/A5086913382","display_name":"Chun\u2010Hsiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Hsiang Wang","raw_affiliation_strings":["National Taiwan University,Dept. of CSIE,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Dept. of CSIE,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054435952","display_name":"Chung-Che Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Che Wang","raw_affiliation_strings":["National Taiwan University,Dept. of CSIE,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Dept. of CSIE,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016862479","display_name":"Jun-You Wang","orcid":"https://orcid.org/0000-0002-9119-9259"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jun-You Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University,Dept. of CSIE,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Dept. of CSIE,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109743054","display_name":"Yen-Hsun Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129806","display_name":"Realtek (China)","ror":"https://ror.org/03sjwka68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210129806"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yen-Hsun Chu","raw_affiliation_strings":["Realtek Semiconductor Corp"],"affiliations":[{"raw_affiliation_string":"Realtek Semiconductor Corp","institution_ids":["https://openalex.org/I4210129806"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086913382"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.7474,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72634791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9904000163078308,"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":0.9847999811172485,"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/computer-science","display_name":"Computer science","score":0.5943924188613892},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5393884181976318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36176496744155884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07182040810585022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5943924188613892},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5393884181976318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36176496744155884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07182040810585022}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800743","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":12,"referenced_works":["https://openalex.org/W1510355813","https://openalex.org/W2127851351","https://openalex.org/W2795374598","https://openalex.org/W2916985722","https://openalex.org/W2963446712","https://openalex.org/W2963750251","https://openalex.org/W3081753361","https://openalex.org/W4372260250","https://openalex.org/W4372271367","https://openalex.org/W4375928773","https://openalex.org/W4391021752","https://openalex.org/W6810177958"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Music":[0],"source":[1],"separation":[2,96,154],"aims":[3],"to":[4,61,85,91,135],"separate":[5],"polyphonic":[6],"music":[7],"into":[8],"different":[9],"types":[10],"of":[11,21,81,105,156],"sources.":[12],"Most":[13],"existing":[14],"methods":[15,40],"focus":[16],"on":[17,35,152],"enhancing":[18],"the":[19,46,79,137,145,153,157],"quality":[20,97],"separated":[22],"results":[23,161],"by":[24],"using":[25],"a":[26,87,93,167,176],"larger":[27],"model":[28],"structure,":[29],"rendering":[30],"them":[31,52],"unsuitable":[32],"for":[33,54,100],"deployment":[34],"edge":[36],"devices.":[37],"Moreover,":[38],"these":[39],"may":[41],"produce":[42],"low-quality":[43],"output":[44],"when":[45],"input":[47],"duration":[48],"is":[49,59,76,84],"short,":[50],"making":[51],"impractical":[53],"real-time":[55,101,128,169],"applications.":[56,102],"This":[57],"challenge":[58],"akin":[60],"those":[62],"in":[63,111,148],"speech":[64],"processing":[65],"models":[66],"and":[67,71,98,122,130,171],"systems,":[68],"where":[69],"isolating":[70],"analyzing":[72],"specific":[73],"audio":[74],"components":[75],"critical.":[77],"Therefore,":[78],"goal":[80],"this":[82,112,149],"paper":[83,150],"enhance":[86],"lightweight":[88],"model,":[89],"MMDenstNet,":[90],"strike":[92],"balance":[94],"between":[95],"latency":[99,132,173],"Different":[103],"directions":[104],"improvement":[106],"are":[107,133],"explored":[108],"or":[109],"proposed":[110],"paper,":[113],"including":[114],"complex":[115],"ideal":[116],"ratio":[117],"mask,":[118],"self-attention,":[119],"band-merge-split":[120],"method,":[121],"feature":[123],"look":[124],"back.":[125],"Source-to-distortion":[126],"ratio,":[127],"factor,":[129],"optimal":[131,172],"employed":[134],"evaluate":[136],"performance.":[138],"To":[139],"align":[140],"with":[141],"our":[142,164],"application":[143],"requirements,":[144],"evaluation":[146],"process":[147],"focuses":[151],"performance":[155],"accompaniment":[158],"part.":[159],"Experimental":[160],"demonstrate":[162],"that":[163],"improvements":[165],"achieve":[166],"low":[168],"factor":[170],"while":[174],"maintaining":[175],"comparable":[177],"source-to-distortion":[178],"ratio.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}