{"id":"https://openalex.org/W2944332341","doi":"https://doi.org/10.1109/iscslp.2018.8706595","title":"Two-Stage Enhancement of Noisy and Reverberant Microphone Array Speech for Automatic Speech Recognition Systems Trained with Only Clean Speech","display_name":"Two-Stage Enhancement of Noisy and Reverberant Microphone Array Speech for Automatic Speech Recognition Systems Trained with Only Clean Speech","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944332341","doi":"https://doi.org/10.1109/iscslp.2018.8706595","mag":"2944332341"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5013004114","display_name":"Quandong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quandong Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032989883","display_name":"Sicheng Wang","orcid":"https://orcid.org/0009-0004-0176-3445"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018911822","display_name":"Fengpei Ge","orcid":"https://orcid.org/0000-0001-5352-1780"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengpei Ge","raw_affiliation_strings":["The Key Laboratory of Speech Acoustic and Content Understanding, Institute of Acoustics, China"],"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustic and Content Understanding, Institute of Acoustics, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115600331","display_name":"Chang Woo Han","orcid":"https://orcid.org/0000-0001-5125-886X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang Woo Han","raw_affiliation_strings":["Samsung Research, Samsung Electronics, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics, Seoul, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329207","display_name":"Jaewon Lee","orcid":"https://orcid.org/0000-0003-3222-5020"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewon Lee","raw_affiliation_strings":["Samsung Research, Samsung Electronics, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics, Seoul, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110949115","display_name":"Lianghao Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianghao Guo","raw_affiliation_strings":["State Key Laboratory of Acoustics, Institute of Acoustics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Acoustics, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"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":["School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5013004114"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.3211,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82523371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"25"},"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":0.9984999895095825,"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":0.9962999820709229,"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/speech-recognition","display_name":"Speech recognition","score":0.817635178565979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7798429727554321},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6550434231758118},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5826188325881958},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5435492992401123},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5233142375946045},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5000519752502441},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48548105359077454},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47926732897758484},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4700585603713989},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4341086745262146},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4279305636882782},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.42092710733413696},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41391921043395996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.323373019695282},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15301641821861267},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08419963717460632},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.06861141324043274}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.817635178565979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798429727554321},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6550434231758118},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5826188325881958},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5435492992401123},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5233142375946045},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5000519752502441},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48548105359077454},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47926732897758484},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4700585603713989},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4341086745262146},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4279305636882782},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.42092710733413696},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41391921043395996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.323373019695282},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15301641821861267},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08419963717460632},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.06861141324043274},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1976805820","https://openalex.org/W2001124347","https://openalex.org/W2003399270","https://openalex.org/W2024490156","https://openalex.org/W2025907885","https://openalex.org/W2039553327","https://openalex.org/W2044893557","https://openalex.org/W2061074721","https://openalex.org/W2066218102","https://openalex.org/W2067584370","https://openalex.org/W2078528584","https://openalex.org/W2099984896","https://openalex.org/W2101609516","https://openalex.org/W2109199922","https://openalex.org/W2113131123","https://openalex.org/W2119817628","https://openalex.org/W2121767183","https://openalex.org/W2124754790","https://openalex.org/W2129934596","https://openalex.org/W2138196899","https://openalex.org/W2141411743","https://openalex.org/W2146871184","https://openalex.org/W2147665979","https://openalex.org/W2150678643","https://openalex.org/W2168729028","https://openalex.org/W2289480995","https://openalex.org/W2292743699","https://openalex.org/W2345067732","https://openalex.org/W2397226255","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2475682732","https://openalex.org/W2542605056","https://openalex.org/W2564155414","https://openalex.org/W2568308529","https://openalex.org/W2605589342","https://openalex.org/W2606806821","https://openalex.org/W2748820902","https://openalex.org/W2772504888","https://openalex.org/W2785517859","https://openalex.org/W3094114204","https://openalex.org/W4206633762","https://openalex.org/W4253928870","https://openalex.org/W6677303870","https://openalex.org/W6697090003","https://openalex.org/W6712317276","https://openalex.org/W6736434074"],"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/W3008816511","https://openalex.org/W4386746628","https://openalex.org/W2294333436","https://openalex.org/W2132495960","https://openalex.org/W2109356272"],"abstract_inverted_index":{"We":[0,22,45],"propose":[1],"a":[2,33,70,95,122,128,133,145,166,172],"two-stage":[3],"approach":[4],"to":[5,24,29,74,90],"enhancement":[6,142],"of":[7,72,94,110,125,130,136,148,152,176,184,195],"far-field":[8],"microphone":[9],"array":[10],"speech":[11,28,36,93,111,149,183,194],"collected":[12],"in":[13,61,66,69,78],"reverberant":[14],"conditions":[15],"corrupted":[16],"by":[17,32,162],"interfering":[18],"speakers":[19],"and":[20,53,84,132,188],"noises.":[21],"intend":[23],"produce":[25],"top-quality":[26],"enhanced":[27,83,182],"be":[30],"used":[31],"black-box":[34],"automatic":[35],"recognition":[37,168],"(ASR)":[38],"system":[39,143],"already":[40],"trained":[41],"with":[42,107],"clean":[43],"speech.":[44],"explore":[46],"different":[47],"deep":[48],"neural":[49],"network":[50],"(DNN)":[51],"architectures":[52],"the":[54,82,99,116,185,196],"best":[55,139],"configuration":[56],"comprises":[57],"two":[58],"stages.":[59],"First,":[60],"pre-enhancement,":[62],"we":[63,80,170],"utilize":[64],"features":[65,86],"temporal":[67],"context":[68],"subset":[71],"microphones":[73,89],"perform":[75],"enhancement.":[76],"Second,":[77],"integration,":[79],"concatenate":[81],"noisy":[85,193],"from":[87,115,155,179,189],"all":[88],"estimate":[91],"anechoic":[92],"reference":[96,197],"channel":[97],"as":[98],"overall":[100],"output.":[101],"Tested":[102],"on":[103],"eight":[104],"speakers,":[105],"each":[106],"5":[108],"minutes":[109],"for":[112,157,165,181,191],"DNN":[113],"training,":[114],"Wall":[117],"Street":[118],"Journal":[119],"corpus,":[120],"at":[121,127],"signal-to-interference-plus-noise-ratio":[123],"level":[124],"5-15dB,":[126],"distance":[129],"l-5m":[131],"reverberation":[134],"time":[135],"0.2-0.3s,":[137],"our":[138,158],"8-channel,":[140],"speaker-dependent":[141],"attains":[144],"perceptual":[146],"evaluation":[147],"quality":[150],"score":[151],"2.95,":[153],"up":[154],"2.43":[156],"single-channel":[159,186],"system.":[160],"Followed":[161],"speaker-independent":[163],"ASR":[164],"230K-word":[167],"task,":[169],"achieve":[171],"word":[173],"error":[174],"rate":[175],"6.56%,":[177],"down":[178],"17.89%":[180],"system,":[187],"48.47%":[190],"unprocessed":[192],"channel.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}