{"id":"https://openalex.org/W4388820412","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317465","title":"Analysis of Speech Separation Performance Degradation on Emotional Speech Mixtures","display_name":"Analysis of Speech Separation Performance Degradation on Emotional Speech Mixtures","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820412","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317465"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY","SG"],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217727","display_name":"Dianwen Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY","SG"],"is_corresponding":false,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Nanyang Technological University, Singapore","Speech Lab of DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chng Eng Siong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chng Eng Siong","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"116","issue":null,"first_page":"2002","last_page":"2007"},"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/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":0.9976999759674072,"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/degradation","display_name":"Degradation (telecommunications)","score":0.7895916700363159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6776975393295288},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.65349280834198},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.641828715801239},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5763621926307678},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4906958341598511},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.46021902561187744},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.43431252241134644},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4203197956085205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3629513382911682},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3393694758415222},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2863742411136627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1137789785861969}],"concepts":[{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.7895916700363159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6776975393295288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.65349280834198},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.641828715801239},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5763621926307678},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4906958341598511},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.46021902561187744},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.43431252241134644},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4203197956085205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3629513382911682},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3393694758415222},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2863742411136627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1137789785861969},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W143173166","https://openalex.org/W1494198834","https://openalex.org/W1991139021","https://openalex.org/W2221409856","https://openalex.org/W2791213618","https://openalex.org/W2891164350","https://openalex.org/W2997399314","https://openalex.org/W3015707499","https://openalex.org/W3027008958","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3185109982","https://openalex.org/W4231257010","https://openalex.org/W4248048444","https://openalex.org/W4297798768","https://openalex.org/W4307478192","https://openalex.org/W4312096533","https://openalex.org/W4312768311","https://openalex.org/W4372342491","https://openalex.org/W4372349540","https://openalex.org/W4375869348","https://openalex.org/W4385756463","https://openalex.org/W6644353974","https://openalex.org/W6752022697","https://openalex.org/W6764637016","https://openalex.org/W6765185461","https://openalex.org/W6777776875","https://openalex.org/W6782183663","https://openalex.org/W6847054494"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W2055243143","https://openalex.org/W4385464961","https://openalex.org/W2060903012","https://openalex.org/W2021161555"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"strides":[2],"made":[3],"in":[4,26,41,59,121],"Speech":[5],"Separation,":[6],"most":[7],"models":[8,25,38,89],"are":[9],"trained":[10],"on":[11,108],"datasets":[12],"with":[13,90,110],"neutral":[14],"emotions.":[15,112],"Emotional":[16],"speech":[17,30,60,123],"has":[18],"been":[19],"known":[20],"to":[21,50,104],"degrade":[22],"performance":[23,53,93],"of":[24,29,36,64,78,102,117],"a":[27,71],"variety":[28],"tasks,":[31],"which":[32],"reduces":[33],"the":[34,52,57,62,115],"effectiveness":[35],"these":[37],"when":[39],"deployed":[40],"real-world":[42,122],"scenarios.":[43],"In":[44],"this":[45],"paper":[46],"we":[47],"perform":[48],"analysis":[49],"differentiate":[51],"degradation":[54,101],"arising":[55],"from":[56,61],"emotions":[58,120],"impact":[63],"out-of-domain":[65,92],"inference.":[66],"This":[67,113],"is":[68],"measured":[69],"using":[70],"carefully":[72],"designed":[73],"test":[74],"dataset,":[75],"Emo2Mix,":[76],"consisting":[77],"balanced":[79],"data":[80],"across":[81],"all":[82],"emotional":[83],"combinations.":[84],"We":[85],"show":[86],"that":[87],"even":[88],"strong":[91,111],"such":[94],"as":[95],"Sepformer":[96],"can":[97],"still":[98],"suffer":[99],"significant":[100],"up":[103],"5.1":[105],"dB":[106],"SI-SDRi":[107],"mixtures":[109],"demonstrates":[114],"importance":[116],"accounting":[118],"for":[119],"separation":[124],"applications.":[125]},"counts_by_year":[],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}