{"id":"https://openalex.org/W3016232124","doi":"https://doi.org/10.1109/icassp40776.2020.9053426","title":"Continuous Speech Separation: Dataset and Analysis","display_name":"Continuous Speech Separation: Dataset and Analysis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016232124","doi":"https://doi.org/10.1109/icassp40776.2020.9053426","mag":"3016232124"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218426","display_name":"Tianyan Zhou","orcid":"https://orcid.org/0000-0003-3238-2982"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyan Zhou","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["One Microsoft Way, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5108961732"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":22.466,"has_fulltext":false,"cited_by_count":208,"citation_normalized_percentile":{"value":0.99739074,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7284","last_page":"7288"},"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":0.9994000196456909,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8164046406745911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6712319254875183},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6180357336997986},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5767228603363037},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5249322056770325},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5126511454582214},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45572274923324585},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.44246217608451843},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4372609257698059},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4286607801914215},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.41066974401474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4086180329322815},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3789255917072296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34994441270828247},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.25504928827285767}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164046406745911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6712319254875183},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6180357336997986},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5767228603363037},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5249322056770325},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5126511454582214},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45572274923324585},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44246217608451843},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4372609257698059},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4286607801914215},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.41066974401474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4086180329322815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3789255917072296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34994441270828247},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.25504928827285767},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W189850294","https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1591607137","https://openalex.org/W2005733316","https://openalex.org/W2030486566","https://openalex.org/W2101045344","https://openalex.org/W2125336414","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2749510669","https://openalex.org/W2786625961","https://openalex.org/W2801798988","https://openalex.org/W2803322398","https://openalex.org/W2884797218","https://openalex.org/W2889503488","https://openalex.org/W2890820256","https://openalex.org/W2891405874","https://openalex.org/W2892163332","https://openalex.org/W2909607850","https://openalex.org/W2910254446","https://openalex.org/W2924115626","https://openalex.org/W2936423518","https://openalex.org/W2938646939","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2960140743","https://openalex.org/W2962865004","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2972693890","https://openalex.org/W2973062255","https://openalex.org/W2975704529","https://openalex.org/W2980986990","https://openalex.org/W2996969697","https://openalex.org/W3007946293","https://openalex.org/W3008283340","https://openalex.org/W3015199127","https://openalex.org/W3099330747","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6631362777","https://openalex.org/W6651792828","https://openalex.org/W6678809451","https://openalex.org/W6754567259","https://openalex.org/W6755462816","https://openalex.org/W6759323020","https://openalex.org/W6765757276","https://openalex.org/W6768815455","https://openalex.org/W6771611251"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W3132176577","https://openalex.org/W2114974607","https://openalex.org/W2150502936","https://openalex.org/W4381327731","https://openalex.org/W3112881379","https://openalex.org/W2158216966","https://openalex.org/W2002298560","https://openalex.org/W2019256813","https://openalex.org/W2969585518"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,124,128,135,148,187],"dataset":[4,204],"and":[5,61,65,170,205],"protocols":[6],"for":[7],"evaluating":[8],"continuous":[9,60,119,136],"speech":[10,15,28,57,79,120,132],"separation":[11,16,39,121],"algorithms.":[12],"Most":[13],"prior":[14],"studies":[17],"use":[18],"pre-segmented":[19],"audio":[20,137,173],"signals,":[21],"which":[22],"are":[23,59,144,208],"typically":[24],"generated":[25],"by":[26,147,162,185,200],"mixing":[27],"utterances":[29,142,166],"on":[30,46],"computers":[31],"so":[32],"that":[33,106,139,143],"they":[34],"fully":[35],"overlap.":[36],"Also,":[37],"the":[38,70,92,96,164,172,213],"algorithms":[40],"have":[41,74],"often":[42],"been":[43],"evaluated":[44],"based":[45],"signal-based":[47,71],"metrics":[48,72],"such":[49],"as":[50,123],"signal-to-distortion":[51],"ratio.":[52],"However,":[53],"in":[54,215],"natural":[55],"conversations,":[56],"signals":[58,133],"contain":[62],"both":[63],"overlapped":[64,146],"overlap-free":[66],"regions.":[67],"In":[68,114],"addition,":[69],"only":[73,84],"weak":[75],"correlation":[76],"with":[77,175],"automatic":[78],"recognition":[80],"(ASR)":[81],"accuracy.":[82],"Not":[83],"does":[85],"this":[86,115,216],"make":[87],"it":[88,99],"hard":[89],"to":[90,111,167,211],"assess":[91],"practical":[93],"relevance":[94],"of":[95,126,130],"tested":[97],"algorithms,":[98],"also":[100],"hinders":[101],"researchers":[102],"from":[103,134,160],"developing":[104],"systems":[105],"can":[107],"be":[108],"readily":[109],"applied":[110],"real":[112,153],"scenarios.":[113],"paper,":[116],"we":[117],"define":[118],"(CSS)":[122],"task":[125],"generating":[127],"set":[129],"non-overlapped":[131],"stream":[138],"contains":[140],"multiple":[141],"partially":[145],"varying":[149],"degree.":[150],"A":[151,178,192],"new":[152],"recording":[154],"dataset,":[155],"called":[156],"LibriCSS,":[157],"is":[158,183,198],"derived":[159],"LibriSpeech":[161],"concatenating":[163],"corpus":[165],"simulate":[168],"conversations":[169],"capturing":[171],"replays":[174],"far-field":[176],"microphones.":[177],"Kaldi-based":[179],"ASR":[180],"evaluation":[181,206],"protocol":[182],"established":[184],"using":[186,201],"well-trained":[188],"multi-conditional":[189],"acoustic":[190],"model.":[191],"recently":[193],"proposed":[194],"speaker-independent":[195],"CSS":[196],"algorithm":[197],"investigated":[199],"LibriCSS.":[202],"The":[203],"scripts":[207],"made":[209],"available":[210],"facilitate":[212],"research":[214],"direction":[217],"<sup":[218],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[219],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[220],".":[221]},"counts_by_year":[{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":41},{"year":2021,"cited_by_count":54},{"year":2020,"cited_by_count":18}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}