{"id":"https://openalex.org/W2884797218","doi":"https://doi.org/10.21437/interspeech.2018-1768","title":"The Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines","display_name":"The Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2884797218","doi":"https://doi.org/10.21437/interspeech.2018-1768","mag":"2884797218"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1768","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.10609","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":["University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":289,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1561","last_page":"1565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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":0.9825000166893005,"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":0.8019313216209412},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7348145842552185},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.6709321737289429},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6466018557548523},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6464288234710693},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6409297585487366},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.582073986530304},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5468907952308655},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5058924555778503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3208468556404114},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10200735926628113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019313216209412},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7348145842552185},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.6709321737289429},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6466018557548523},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6464288234710693},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6409297585487366},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.582073986530304},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5468907952308655},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5058924555778503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3208468556404114},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10200735926628113},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1768","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.10609","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10609","pdf_url":"https://arxiv.org/pdf/1803.10609","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":"","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.10609","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10609","pdf_url":"https://arxiv.org/pdf/1803.10609","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G3872131408","display_name":"Robust voice command adapted to the user and to the context for AAL","funder_award_id":"ANR-16-CE33-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2884797218.pdf","grobid_xml":"https://content.openalex.org/works/W2884797218.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W72302491","https://openalex.org/W111896636","https://openalex.org/W179707045","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W2000221426","https://openalex.org/W2032595071","https://openalex.org/W2040039958","https://openalex.org/W2046317813","https://openalex.org/W2070707809","https://openalex.org/W2112865675","https://openalex.org/W2148613904","https://openalex.org/W2166637769","https://openalex.org/W2170579896","https://openalex.org/W2250629451","https://openalex.org/W2251711535","https://openalex.org/W2288371874","https://openalex.org/W2404199887","https://openalex.org/W2490695385","https://openalex.org/W2502139158","https://openalex.org/W2510616059","https://openalex.org/W2514741789","https://openalex.org/W2533523411","https://openalex.org/W2559260703","https://openalex.org/W2559809918","https://openalex.org/W2766219058","https://openalex.org/W2899771611","https://openalex.org/W2918296821","https://openalex.org/W2963127222","https://openalex.org/W2963266252","https://openalex.org/W4249905609","https://openalex.org/W4298298427","https://openalex.org/W4302156456"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2900122540","https://openalex.org/W2122030153","https://openalex.org/W2963983801","https://openalex.org/W3119734852","https://openalex.org/W2804363668"],"abstract_inverted_index":{"The":[0,77],"CHiME":[1,32],"challenge":[2,121],"series":[3],"aims":[4],"to":[5,57,100,106],"advance":[6],"robust":[7],"automatic":[8],"speech\\nrecognition":[9],"(ASR)":[10],"technology":[11],"by":[12,68],"promoting":[13],"research":[14],"at":[15],"the":[16,30,36,110,120,128,131,134],"interface":[17],"of":[18,38,62,109,127],"speech\\nand":[19],"language":[20,114],"processing,":[21],"signal":[22],"processing":[23],",":[24],"and":[25,66,72,82,122,133,141,143],"machine":[26],"learning.":[27],"This":[28],"paper\\nintroduces":[29],"5th":[31],"Challenge,":[33],"which":[34],"considers":[35],"task":[37,111],"distant\\nmulti-microphone":[39],"conversational":[40,64,113],"ASR":[41],"in":[42],"real":[43],"home":[44],"environments.":[45],"Speech":[46],"material\\nwas":[47],"elicited":[48],"using":[49],"a":[50,79,83,124],"dinner":[51],"party":[52],"scenario":[53],"with":[54],"efforts":[55],"taken":[56],"capture":[58,102],"data\\nthat":[59],"is":[60],"representative":[61],"natural":[63],"speech":[65,139],"recorded":[67],"6\\nKinect":[69],"microphone":[70,75],"arrays":[71],"4":[73],"binaural":[74],"pairs.":[76],"challenge\\nfeatures":[78],"single-array":[80],"track":[81,85],"multiple-array":[84],"and,":[86],"for":[87,94,119,137],"each":[88],"track,\\ndistinct":[89],"rankings":[90],"will":[91],"be":[92],"produced":[93],"systems":[95,104,136],"focusing":[96],"on":[97],"robustness":[98],"with\\nrespect":[99],"distant-microphone":[101],"vs.":[103],"attempting":[105],"address":[107],"all\\naspects":[108],"including":[112],"modeling.":[115],"We":[116],"discuss":[117],"the\\nrationale":[118],"provide":[123],"detailed":[125],"description":[126],"data\\ncollection":[129],"procedure,":[130],"task,":[132],"baseline":[135],"array\\nsynchronization,":[138],"enhancement,":[140],"conventional":[142],"end-to-end":[144],"ASR.\\n":[145]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":40},{"year":2022,"cited_by_count":44},{"year":2021,"cited_by_count":47},{"year":2020,"cited_by_count":45},{"year":2019,"cited_by_count":53},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}