{"id":"https://openalex.org/W2948312300","doi":"https://doi.org/10.1109/jstsp.2019.2920764","title":"A Speaker-Dependent Approach to Separation of Far-Field Multi-Talker Microphone Array Speech for Front-End Processing in the CHiME-5 Challenge","display_name":"A Speaker-Dependent Approach to Separation of Far-Field Multi-Talker Microphone Array Speech for Front-End Processing in the CHiME-5 Challenge","publication_year":2019,"publication_date":"2019-06-03","ids":{"openalex":"https://openalex.org/W2948312300","doi":"https://doi.org/10.1109/jstsp.2019.2920764","mag":"2948312300"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2920764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2920764","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455"},"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":"Lei Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7680-6455","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590046","display_name":"Tian Gao","orcid":"https://orcid.org/0000-0002-9523-5560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["iFlytek, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9523-5560","affiliations":[{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067418255","display_name":"Yi Fang","orcid":"https://orcid.org/0000-0002-1538-249X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Fang","raw_affiliation_strings":["iFlytek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089891264","display_name":"Feng Ma","orcid":"https://orcid.org/0000-0002-6539-0965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Ma","raw_affiliation_strings":["iFlytek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3088,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80759335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"13","issue":"4","first_page":"827","last_page":"840"},"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":0.9980999827384949,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.777551531791687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7561703324317932},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5959121584892273},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5576989650726318},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5454497933387756},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5288454294204712},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47036075592041016},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46129879355430603},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44243863224983215},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4395974576473236},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.41844046115875244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32658639550209045},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16416415572166443}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.777551531791687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561703324317932},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5959121584892273},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5576989650726318},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5454497933387756},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5288454294204712},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47036075592041016},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46129879355430603},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44243863224983215},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4395974576473236},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.41844046115875244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32658639550209045},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16416415572166443},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2019.2920764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2920764","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G573022218","display_name":null,"funder_award_id":"U1613211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8173470123","display_name":"\u57fa\u4e8e\u56de\u5f52\u795e\u7ecf\u7f51\u7edc\u7684\u8bed\u97f3\u5206\u79bb\u5173\u952e\u95ee\u9898\u7814\u7a76","funder_award_id":"61671422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W108815450","https://openalex.org/W781582143","https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1524333225","https://openalex.org/W1897240248","https://openalex.org/W1968939597","https://openalex.org/W1983812858","https://openalex.org/W1989314204","https://openalex.org/W1991139021","https://openalex.org/W2013608223","https://openalex.org/W2024490156","https://openalex.org/W2046869671","https://openalex.org/W2050875687","https://openalex.org/W2069681747","https://openalex.org/W2069884666","https://openalex.org/W2070707809","https://openalex.org/W2072548008","https://openalex.org/W2078528584","https://openalex.org/W2083751884","https://openalex.org/W2087368178","https://openalex.org/W2091432990","https://openalex.org/W2093225945","https://openalex.org/W2099741732","https://openalex.org/W2101045344","https://openalex.org/W2114461480","https://openalex.org/W2121767183","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2129934596","https://openalex.org/W2134642725","https://openalex.org/W2135823751","https://openalex.org/W2141411743","https://openalex.org/W2144763279","https://openalex.org/W2148613904","https://openalex.org/W2152131029","https://openalex.org/W2158143227","https://openalex.org/W2164764235","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2289731793","https://openalex.org/W2460742184","https://openalex.org/W2513383847","https://openalex.org/W2514741789","https://openalex.org/W2540419083","https://openalex.org/W2558649592","https://openalex.org/W2586584460","https://openalex.org/W2605589342","https://openalex.org/W2610674366","https://openalex.org/W2734774145","https://openalex.org/W2749337587","https://openalex.org/W2765976216","https://openalex.org/W2884797218","https://openalex.org/W2891433113","https://openalex.org/W2918296821","https://openalex.org/W2962866211","https://openalex.org/W2991015288","https://openalex.org/W3131736947","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W6622670569","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2380771148","https://openalex.org/W4408354526","https://openalex.org/W2348931051","https://openalex.org/W2538903081","https://openalex.org/W2389562147","https://openalex.org/W3195050710","https://openalex.org/W3008816511","https://openalex.org/W4386746628","https://openalex.org/W3188266982","https://openalex.org/W2294333436"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,43,57,73,92,102,126,158],"novel":[3],"speaker-dependent":[4],"speech":[5,32,36,62,69,76,90,121,168],"separation":[6,77,124],"framework":[7],"for":[8,29,138,164],"the":[9,109,112,116,140,143,148,153,173,179,191,210],"challenging":[10],"CHiME-5":[11,211],"acoustic":[12],"environments,":[13],"exploiting":[14],"advantages":[15],"of":[16,45,91,104,108,161,167,187],"both":[17],"deep":[18,59],"learning":[19,60],"based":[20,61,131],"and":[21,54,56,115,123,195],"conventional":[22],"preprocessing":[23],"techniques":[24],"to":[25,50,67,88,209],"prepare":[26],"data":[27,163],"effectively":[28],"separating":[30],"target":[31,93,113],"from":[33,84,95,119],"multi-talker":[34],"mixed":[35,99],"collected":[37],"with":[38],"multiple":[39],"microphone":[40],"arrays.":[41],"First,":[42],"series":[44],"multi-channel":[46],"operations":[47],"is":[48,65,86,135],"conducted":[49],"reduce":[51],"existing":[52],"reverberation":[53],"noise,":[55,111],"single-channel":[58,120],"enhancement":[63,122],"model":[64,130],"used":[66,137],"predict":[68],"presence":[70],"probabilities.":[71],"Next,":[72],"two-stage":[74,181],"supervised":[75],"approach,":[78],"using":[79],"oracle":[80],"speaker":[81,94,114,149],"diarization":[82],"information":[83],"CHiME-5,":[85],"proposed":[87,154,180],"separate":[89],"interference":[96,117],"speakers":[97,118],"in":[98,199],"speech.":[100],"Given":[101],"set":[103,175],"three":[105],"estimated":[106],"masks":[107],"background":[110],"models,":[125],"complex":[127],"Gaussian":[128],"mixture":[129],"generalized":[132],"eigenvalue":[133],"beamformer":[134],"then":[136],"enhancing":[139],"signal":[141],"at":[142],"reference":[144],"array":[145],"while":[146],"avoiding":[147],"permutation":[150],"issue.":[151],"Furthermore,":[152],"front-end":[155],"can":[156,183],"generate":[157],"large":[159],"variety":[160],"processed":[162],"an":[165],"ensemble":[166],"recognition":[169,188],"results.":[170],"Experiments":[171],"on":[172],"development":[174],"have":[176],"shown":[177],"that":[178],"approach":[182],"yield":[184],"significant":[185],"improvements":[186],"performance":[189],"over":[190],"official":[192],"baseline":[193],"system":[194],"achieved":[196],"top":[197],"accuracies":[198],"all":[200,206],"four":[201],"competing":[202],"evaluation":[203],"categories":[204],"among":[205],"systems":[207],"submitted":[208],"Challenge.":[212]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}