{"id":"https://openalex.org/W2938297719","doi":"https://doi.org/10.1109/icassp.2019.8682581","title":"Robust Recognition of Reverberant and Noisy Speech Using Coherence-based Processing","display_name":"Robust Recognition of Reverberant and Noisy Speech Using Coherence-based Processing","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938297719","doi":"https://doi.org/10.1109/icassp.2019.8682581","mag":"2938297719"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5042577114","display_name":"Anjali Menon","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjali Menon","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684423","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-2526-4371"},"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":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069424860","display_name":"Richard M. Stern","orcid":"https://orcid.org/0000-0003-0557-7282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard M. Stern","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02477327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"6775","last_page":"6779"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.838523805141449},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8366308212280273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7741371393203735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7514128684997559},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7168020606040955},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6419687867164612},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6169254779815674},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5635236501693726},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.531475841999054},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5244962573051453},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5235628485679626},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45376765727996826},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4106552004814148},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.37618035078048706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31786781549453735},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.1983071267604828},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09826704859733582},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08173435926437378},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.061313092708587646}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.838523805141449},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8366308212280273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7741371393203735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7514128684997559},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7168020606040955},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6419687867164612},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6169254779815674},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5635236501693726},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.531475841999054},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5244962573051453},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5235628485679626},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45376765727996826},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4106552004814148},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.37618035078048706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31786781549453735},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.1983071267604828},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09826704859733582},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08173435926437378},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.061313092708587646},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W118588063","https://openalex.org/W167318317","https://openalex.org/W1524075427","https://openalex.org/W1524333225","https://openalex.org/W1529608332","https://openalex.org/W1586342741","https://openalex.org/W1973681148","https://openalex.org/W1977949126","https://openalex.org/W2024490156","https://openalex.org/W2025127228","https://openalex.org/W2030486566","https://openalex.org/W2080145918","https://openalex.org/W2104204079","https://openalex.org/W2104695149","https://openalex.org/W2110322414","https://openalex.org/W2117678320","https://openalex.org/W2122171611","https://openalex.org/W2161336374","https://openalex.org/W2164502538","https://openalex.org/W2482792214","https://openalex.org/W6631362777","https://openalex.org/W6631682488","https://openalex.org/W6683785785"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W1970883244","https://openalex.org/W4367280804","https://openalex.org/W2333494157","https://openalex.org/W2076135780","https://openalex.org/W1987603461","https://openalex.org/W2080716336","https://openalex.org/W155806678","https://openalex.org/W1972459890","https://openalex.org/W4251652875"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,172],"combination":[4,140],"of":[5,39,94,98,105,122,133,141,174],"techniques":[6,21,143,166],"for":[7],"improving":[8],"speech":[9,42,101,107,152,158],"recognition":[10,153,159],"accuracy":[11],"using":[12],"two":[13],"microphones":[14],"in":[15,68,77,135,151,168],"reverberant":[16,75,78],"and":[17,25,44,177],"noisy":[18],"environments.":[19,79],"These":[20],"include":[22],"both":[23],"monaural":[24,32],"binaural":[26],"processing.":[27],"The":[28,80],"first":[29],"stage":[30,82],"is":[31,116,144],"precedence-based":[33],"processing":[34],"that":[35,49,109,124],"enhances":[36],"the":[37,40,64,70,74,95,99,106,120,136,165],"onsets":[38],"incoming":[41,100],"signal,":[43],"hence":[45],"suppresses":[46],"later":[47],"components":[48,89,123],"are":[50,110,113,125],"more":[51],"affected":[52],"by":[53,127],"reverberation.":[54],"Onset":[55],"enhancement":[56],"has":[57],"been":[58],"shown":[59,145],"to":[60,63,87,118,146,148,163],"be":[61],"useful":[62],"human":[65],"auditory":[66],"system":[67,160],"separating":[69],"direct":[71],"field":[72,76],"from":[73],"second":[81],"applies":[83],"emphasis":[84],"or":[85,130],"suppression":[86],"signal":[88,108],"based":[90],"on":[91],"an":[92],"estimation":[93],"inter-microphone":[96],"coherence":[97],"signal.":[102,138],"Specifically,":[103],"portions":[104],"less":[111],"coherent":[112],"suppressed,":[114],"which":[115],"intended":[117],"reduce":[119],"contributions":[121],"dominated":[126],"diffuse":[128],"noise":[129],"high":[131],"degrees":[132],"reverberation":[134,175],"input":[137],"A":[139,155],"these":[142],"lead":[147],"significant":[149],"improvements":[150],"accuracy.":[154],"DNN-based":[156],"automatic":[157],"was":[161],"used":[162],"evaluate":[164],"described":[167],"this":[169],"study":[170],"over":[171],"range":[173],"times":[176],"signal-to-interferer":[178],"ratios.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}