{"id":"https://openalex.org/W3149201639","doi":"https://doi.org/10.21437/interspeech.2021-1397","title":"AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario","display_name":"AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3149201639","doi":"https://doi.org/10.21437/interspeech.2021-1397","mag":"3149201639"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1397","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.03603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010250251","display_name":"Yihui Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891716","display_name":"Luyao Cheng","orcid":"https://orcid.org/0009-0006-1311-8448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luyao Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017208328","display_name":"Shubo Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shubo Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031232410","display_name":"Yukai Jv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukai Jv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087994947","display_name":"Yuxiang Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Kong","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","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":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101330960","display_name":"Yanxin Hu","orcid":"https://orcid.org/0009-0009-4388-8883"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxin Hu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"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":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791717","display_name":"Hui Bu","orcid":"https://orcid.org/0000-0003-1883-8496"},"institutions":[{"id":"https://openalex.org/I7923278","display_name":"Shell (Netherlands)","ror":"https://ror.org/00b5m4j81","country_code":"NL","type":"company","lineage":["https://openalex.org/I7923278"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hui Bu","raw_affiliation_strings":["Shell (Netherlands), The Hague, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shell (Netherlands), The Hague, Netherlands","institution_ids":["https://openalex.org/I7923278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696102","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-0748-3669"},"institutions":[{"id":"https://openalex.org/I7923278","display_name":"Shell (Netherlands)","ror":"https://ror.org/00b5m4j81","country_code":"NL","type":"company","lineage":["https://openalex.org/I7923278"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["Shell (Netherlands), The Hague, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shell (Netherlands), The Hague, Netherlands","institution_ids":["https://openalex.org/I7923278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3665","last_page":"3669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.7821686267852783},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7769773006439209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7685245871543884},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5888351202011108},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5547293424606323},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5140484571456909},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.48979973793029785},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4828956127166748},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.47255298495292664},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4702008366584778},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41657760739326477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2994770109653473},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17701533436775208},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0883932113647461},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0836423933506012},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.08102363348007202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821686267852783},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7769773006439209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7685245871543884},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5888351202011108},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5547293424606323},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5140484571456909},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.48979973793029785},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4828956127166748},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.47255298495292664},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4702008366584778},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41657760739326477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2994770109653473},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17701533436775208},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0883932113647461},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0836423933506012},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.08102363348007202},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1397","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.03603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.03603","pdf_url":"https://arxiv.org/pdf/2104.03603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3149201639","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.03603v4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.03603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.03603","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.03603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.03603","pdf_url":"https://arxiv.org/pdf/2104.03603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3149201639.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W1589137271","https://openalex.org/W1591607137","https://openalex.org/W2000221426","https://openalex.org/W2112865675","https://openalex.org/W2138730338","https://openalex.org/W2166637769","https://openalex.org/W2170579896","https://openalex.org/W2221409856","https://openalex.org/W2508048623","https://openalex.org/W2726515241","https://openalex.org/W2766219058","https://openalex.org/W2889048668","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2969985801","https://openalex.org/W2972541922","https://openalex.org/W2981087920","https://openalex.org/W2981461916","https://openalex.org/W2996322586","https://openalex.org/W3008283340","https://openalex.org/W3015191643","https://openalex.org/W3015598461","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3027008958","https://openalex.org/W3094005623","https://openalex.org/W3094007021","https://openalex.org/W3115133930","https://openalex.org/W3133834828","https://openalex.org/W3140783160","https://openalex.org/W3143843080"],"related_works":["https://openalex.org/W2083691421","https://openalex.org/W3163132306","https://openalex.org/W2081074144","https://openalex.org/W2733679854","https://openalex.org/W1551270940","https://openalex.org/W1578739082","https://openalex.org/W2891237889","https://openalex.org/W89927899","https://openalex.org/W2085242515","https://openalex.org/W1980581885","https://openalex.org/W2911845330","https://openalex.org/W2157850507","https://openalex.org/W2611760243","https://openalex.org/W2163040740","https://openalex.org/W2963040451","https://openalex.org/W2620275798","https://openalex.org/W2900496645","https://openalex.org/W2163704482","https://openalex.org/W2516631658","https://openalex.org/W2462752746"],"abstract_inverted_index":{"In":[0],"this":[1,184],"paper,":[2],"we":[3],"present":[4],"AISHELL-4,":[5],"a":[6,39,170],"sizable":[7],"real-recorded":[8],"Mandarin":[9,153],"speech":[10,19,75,83,121,124,165],"dataset":[11,25,46,142,154],"collected":[12],"by":[13],"8-channel":[14],"circular":[15],"microphone":[16],"array":[17],"for":[18,99,143,155,161],"processing":[20,55],"in":[21,61,77,102,112,147,164,183],"conference":[22],"scenario.":[23],"The":[24],"consists":[26],"of":[27,42,135],"211":[28],"recorded":[29,66],"meeting":[30,101,113],"sessions,":[31],"each":[32,100],"containing":[33],"4":[34],"to":[35,48,108,129,179],"8":[36],"speakers,":[37],"with":[38],"total":[40],"length":[41],"120":[43],"hours.":[44],"This":[45,104],"aims":[47],"bridge":[49],"the":[50,57,106,151],"advanced":[51],"research":[52,182],"on":[53],"multi-speaker":[54,144],"and":[56,72,93,126,132,173],"practical":[58],"application":[59],"scenario":[60],"three":[62],"aspects.":[63],"With":[64],"real":[65],"meetings,":[67],"AISHELL-4":[68,149],"provides":[69],"realistic":[70],"acoustics":[71],"rich":[73],"natural":[74],"characteristics":[76],"conversation":[78,156],"such":[79,119],"as":[80,120,176],"short":[81],"pause,":[82],"overlap,":[84],"quick":[85],"speaker":[86,94,127],"turn,":[87],"noise,":[88],"etc.":[89],"Meanwhile,":[90],"accurate":[91],"transcription":[92],"voice":[95],"activity":[96],"are":[97,146],"provided":[98],"AISHELL-4.":[103],"allows":[105],"researchers":[107],"explore":[109],"different":[110],"aspects":[111],"processing,":[114,123],"ranging":[115],"from":[116],"individual":[117],"tasks":[118,145],"front-end":[122],"recognition":[125],"diarization,":[128],"multi-modality":[130],"modeling":[131],"joint":[133],"optimization":[134],"relevant":[136],"tasks.":[137],"Given":[138],"most":[139],"open":[140],"source":[141],"English,":[148],"is":[150],"only":[152],"speech,":[157],"providing":[158],"additional":[159],"value":[160],"data":[162],"diversity":[163],"community.":[166],"We":[167],"also":[168],"release":[169],"PyTorch-based":[171],"training":[172],"evaluation":[174],"framework":[175],"baseline":[177],"system":[178],"promote":[180],"reproducible":[181],"field.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
