{"id":"https://openalex.org/W2288645994","doi":"https://doi.org/10.1109/asru.2015.7404828","title":"The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices","display_name":"The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2288645994","doi":"https://doi.org/10.1109/asru.2015.7404828","mag":"2288645994"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101438174","display_name":"Nobutaka Ito","orcid":"https://orcid.org/0000-0001-9740-6848"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ito","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040951732","display_name":"Chengzhu Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengzhu Yu","raw_affiliation_strings":["University of Texas, Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Dallas","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057427428","display_name":"Wojciech J. Fabian","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wojciech J. Fabian","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039277089","display_name":"Miquel Espi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miquel Espi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Higuchi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"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":236,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"443"},"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":0.9995999932289124,"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":0.9991000294685364,"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":0.780559778213501},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6900930404663086},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6296830177307129},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5848485231399536},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5817813873291016},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5383582711219788},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5106440186500549},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5093425512313843},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.41267162561416626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33502358198165894},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1125749945640564},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09032723307609558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780559778213501},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6900930404663086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6296830177307129},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5848485231399536},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5817813873291016},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5383582711219788},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5106440186500549},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5093425512313843},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.41267162561416626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33502358198165894},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1125749945640564},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09032723307609558},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W330298975","https://openalex.org/W1799366690","https://openalex.org/W1973669708","https://openalex.org/W1983812858","https://openalex.org/W1985261152","https://openalex.org/W1995562189","https://openalex.org/W2003203076","https://openalex.org/W2010362084","https://openalex.org/W2014768838","https://openalex.org/W2031583051","https://openalex.org/W2033310064","https://openalex.org/W2039716246","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2066378046","https://openalex.org/W2097117768","https://openalex.org/W2098318492","https://openalex.org/W2100335648","https://openalex.org/W2116064496","https://openalex.org/W2119203697","https://openalex.org/W2131342762","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2156393451","https://openalex.org/W2160650576","https://openalex.org/W2161513525","https://openalex.org/W2171784699","https://openalex.org/W2185726469","https://openalex.org/W2188162373","https://openalex.org/W2289394825","https://openalex.org/W2328757576","https://openalex.org/W2400339399","https://openalex.org/W2534981247","https://openalex.org/W2616139854","https://openalex.org/W2762693443","https://openalex.org/W6638444622","https://openalex.org/W6674864272","https://openalex.org/W6674914833","https://openalex.org/W6686978693","https://openalex.org/W6702079475","https://openalex.org/W6745258804"],"related_works":["https://openalex.org/W2161947961","https://openalex.org/W1930652678","https://openalex.org/W1769849273","https://openalex.org/W1491017269","https://openalex.org/W2907228390","https://openalex.org/W1488173215","https://openalex.org/W2290075840","https://openalex.org/W3216527012","https://openalex.org/W2185164075","https://openalex.org/W2950036573"],"abstract_inverted_index":{"CHiME-3":[0,27],"is":[1],"a":[2,116,122],"research":[3],"community":[4],"challenge":[5],"organised":[6],"in":[7,19,63],"2015":[8],"to":[9,68,133],"evaluate":[10],"speech":[11,32],"recognition":[12,35,104],"systems":[13,129],"for":[14,46],"mobile":[15],"multi-microphone":[16,85],"devices":[17],"used":[18],"noisy":[20],"daily":[21],"environments.":[22],"This":[23],"paper":[24],"describes":[25],"NTT's":[26],"system,":[28],"which":[29],"integrates":[30],"advanced":[31,111],"enhancement":[33],"and":[34,51,88,121],"techniques.":[36],"Newly":[37],"developed":[38,132],"techniques":[39,101],"include":[40,84],"the":[41,61,78],"use":[42],"of":[43,91],"spectral":[44],"masks":[45],"acoustic":[47,52],"beam-steering":[48],"vector":[49],"estimation":[50],"modelling":[53],"with":[54,94,136],"deep":[55],"convolutional":[56],"neural":[57,92],"networks":[58,93],"based":[59],"on":[60,103],"\"network":[62],"network\"":[64],"concept.":[65],"In":[66],"addition":[67],"these":[69,100,110],"improvements,":[70],"our":[71,113],"system":[72,114],"has":[73],"several":[74],"key":[75],"differences":[76,83],"from":[77],"official":[79],"baseline":[80],"system.":[81],"The":[82,97],"training,":[86],"dereverberation,":[87],"cross":[89],"adaptation":[90],"different":[95],"architectures.":[96],"impacts":[98],"that":[99],"have":[102],"performance":[105],"are":[106,130],"investigated.":[107],"By":[108],"combining":[109],"techniques,":[112],"achieves":[115],"3.45%":[117],"development":[118],"error":[119,125],"rate":[120],"5.83%":[123],"evaluation":[124],"rate.":[126],"Three":[127],"simpler":[128],"also":[131],"perform":[134],"evaluations":[135],"constrained":[137],"set-ups.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":47},{"year":2017,"cited_by_count":43},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
