{"id":"https://openalex.org/W4384160435","doi":"https://doi.org/10.1109/taslp.2023.3290428","title":"Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks","display_name":"Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4384160435","doi":"https://doi.org/10.1109/taslp.2023.3290428"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3290428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3290428","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5018337836","display_name":"Darius Petermann","orcid":"https://orcid.org/0000-0002-5973-5752"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Darius Petermann","raw_affiliation_strings":["Department of Intelligent Systems Engineering, Indiana University Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems Engineering, Indiana University Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Shanmugam Subramanian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","the Microsoft Corporation, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"the Microsoft Corporation, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018337836"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":2.1791,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88530688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"2592","last_page":"2605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7310191988945007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7127811312675476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6283009648323059},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6057912707328796}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7310191988945007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127811312675476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6283009648323059},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6057912707328796},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3290428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3290428","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315072","display_name":"Mitsubishi Electric Research Laboratories","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1568033255","https://openalex.org/W1568645074","https://openalex.org/W2101593488","https://openalex.org/W2118497033","https://openalex.org/W2123843894","https://openalex.org/W2153331367","https://openalex.org/W2221409856","https://openalex.org/W2408239454","https://openalex.org/W2526050071","https://openalex.org/W2580221632","https://openalex.org/W2593116425","https://openalex.org/W2735559731","https://openalex.org/W2760103357","https://openalex.org/W2761108741","https://openalex.org/W2885307078","https://openalex.org/W2898963093","https://openalex.org/W2943934118","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2972411915","https://openalex.org/W2972541922","https://openalex.org/W2982456909","https://openalex.org/W2984935418","https://openalex.org/W2990666817","https://openalex.org/W2998490864","https://openalex.org/W2998616931","https://openalex.org/W2998657200","https://openalex.org/W2998733532","https://openalex.org/W3015190346","https://openalex.org/W3015213533","https://openalex.org/W3015315843","https://openalex.org/W3015371781","https://openalex.org/W3095263845","https://openalex.org/W3095738461","https://openalex.org/W3097777922","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3104704316","https://openalex.org/W3145029257","https://openalex.org/W3151851237","https://openalex.org/W3160050861","https://openalex.org/W3160071434","https://openalex.org/W3161744562","https://openalex.org/W3161935490","https://openalex.org/W3169030202","https://openalex.org/W3170881237","https://openalex.org/W3185389098","https://openalex.org/W3205879560","https://openalex.org/W3208713760","https://openalex.org/W3209059054","https://openalex.org/W3213240302","https://openalex.org/W4205689591","https://openalex.org/W4210493250","https://openalex.org/W4221153233","https://openalex.org/W4226153886","https://openalex.org/W4226390724","https://openalex.org/W4287694193","https://openalex.org/W4293998423","https://openalex.org/W4296068829","https://openalex.org/W4297775537","https://openalex.org/W4297797459","https://openalex.org/W4297841603","https://openalex.org/W4298310324","https://openalex.org/W4394661832","https://openalex.org/W6634123395","https://openalex.org/W6675574810","https://openalex.org/W6732646663","https://openalex.org/W6737664043","https://openalex.org/W6744463207","https://openalex.org/W6766320909","https://openalex.org/W6769802879","https://openalex.org/W6781130467","https://openalex.org/W6781762595","https://openalex.org/W6799044462","https://openalex.org/W6842624365"],"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/W2376932109","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Emulating":[0],"the":[1,6,38,63,124,143,149,174,186,196],"human":[2,113],"ability":[3],"to":[4,47,76,155,173,182],"solve":[5],"cocktail":[7,39],"party":[8],"problem,":[9,41],"i.e.,":[10],"focus":[11,36],"on":[12,37,92,148],"a":[13,18,23,44,57,153,222],"source":[14,29,48,89,120,158,166,199],"of":[15,27,67,128,145,195,225],"interest":[16],"in":[17,171],"complex":[19],"acoustic":[20],"scene,":[21],"is":[22,178,239],"long":[24],"standing":[25],"goal":[26],"audio":[28,53,134],"separation":[30,49,90,121,159,167,187],"research.":[31],"In":[32],"this":[33,93],"paper,":[34],"we":[35,116,163,190],"fork":[40],"which":[42],"takes":[43],"three-pronged":[45],"approach":[46],"by":[50,185],"separating":[51],"an":[52],"mixture":[54],"such":[55,99],"as":[56,100,104,106,152],"movie":[58],"soundtrack":[59],"or":[60],"podcast":[61],"into":[62],"three":[64,150,197],"broad":[65],"categories":[66],"speech,":[68],"music,":[69],"and":[70,80,133,138,160,208,218,234,244],"sound":[71,82],"effects":[72],"(SFX":[73],"-":[74],"understood":[75],"include":[77],"ambient":[78],"noise":[79],"natural":[81],"events).":[83],"We":[84,140,213],"evaluate":[85,118],"several":[86],"deep":[87],"learning-based":[88],"models":[91],"task":[94,144],"using":[95],"simple":[96],"objective":[97,107],"measures":[98],"signal-to-distortion":[101],"ratio":[102],"(SDR)":[103],"well":[105],"metrics":[108],"that":[109,165,215],"better":[110],"correlate":[111],"with":[112],"perception.":[114],"Furthermore,":[115],"thoroughly":[117,191],"how":[119,193],"can":[122,205],"influence":[123],"downstream":[125],"transcription":[126,169,211],"asks":[127],"speech":[129,132,229],"recognition":[130,230],"for":[131,136,241],"tagging":[135,242],"music":[137,217,243],"SFX.":[139],"also":[141],"investigate":[142,192],"activity":[146],"detection":[147],"sources":[151],"way":[154],"further":[156],"improve":[157,210],"transcription.":[161],"While":[162],"observe":[164],"improves":[168],"performance":[170,177],"comparison":[172],"original":[175],"soundtrack,":[176],"still":[179],"sub-optimal":[180],"due":[181],"artifacts":[183,207],"introduced":[184],"process.":[188],"Therefore,":[189],"remixing":[194,216,238],"separated":[198],"stems":[200],"at":[201,221],"various":[202],"relative":[203],"levels":[204],"reduce":[206],"consequently":[209],"performance.":[212],"find":[214],"SFX":[219,245],"interferences":[220],"target":[223],"SNR":[224],"17.5":[226],"dB":[227],"reduces":[228],"word":[231],"error":[232],"rate,":[233],"similar":[235],"impact":[236],"from":[237],"observed":[240],"content.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}