{"id":"https://openalex.org/W2718052359","doi":"https://doi.org/10.1109/icassp.2017.7952161","title":"A speech enhancement algorithm by iterating single- and multi-microphone processing and its application to robust ASR","display_name":"A speech enhancement algorithm by iterating single- and multi-microphone processing and its application to robust ASR","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2718052359","doi":"https://doi.org/10.1109/icassp.2017.7952161","mag":"2718052359"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"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":76,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"280"},"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":0.9968000054359436,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503789663314819},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.733018696308136},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6995756030082703},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6878944039344788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6830929517745972},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5554870367050171},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5553793907165527},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5478075742721558},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5065079927444458},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4547842741012573},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38178688287734985},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.3138987421989441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30814164876937866},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.30450379848480225},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0942297875881195},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08216428756713867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503789663314819},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.733018696308136},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6995756030082703},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6878944039344788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6830929517745972},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5554870367050171},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5553793907165527},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5478075742721558},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5065079927444458},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4547842741012573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38178688287734985},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.3138987421989441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30814164876937866},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30450379848480225},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0942297875881195},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08216428756713867},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1665214252","https://openalex.org/W2046317813","https://openalex.org/W2069681747","https://openalex.org/W2144244295","https://openalex.org/W2146502635","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2168379380","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W4245919820","https://openalex.org/W6631362777","https://openalex.org/W6637242042","https://openalex.org/W6681435938"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2900122540","https://openalex.org/W2396048001","https://openalex.org/W4240587264","https://openalex.org/W2348931051","https://openalex.org/W1559044324"],"abstract_inverted_index":{"We":[0],"propose":[1,90],"a":[2,19,43,54,63,76,91,122,137,146],"speech":[3,26,107,141],"enhancement":[4],"algorithm":[5,17,133,165],"based":[6],"on":[7,153],"single-":[8],"and":[9,27,51,82,144],"multi-microphone":[10,72],"processing":[11],"techniques.":[12],"The":[13,131],"core":[14],"of":[15,42,59,80,102,159],"the":[16,24,39,57,97,100,105,127,154,162],"estimates":[18],"time-frequency":[20],"mask":[21,55,114],"which":[22],"represents":[23],"target":[25],"use":[28],"masking-based":[29,92],"beamforming":[30],"to":[31,94,111],"enhance":[32],"corrupted":[33],"speech.":[34,130],"Specifically,":[35],"in":[36,71,99],"single-microphone":[37],"processing,":[38,73],"received":[40],"signals":[41,50],"microphone":[44,61],"array":[45],"are":[46,119],"treated":[47],"as":[48,136],"individual":[49],"we":[52,74,89,125],"estimate":[53],"for":[56,85,113,121,139],"signal":[58],"each":[60],"using":[62],"deep":[64],"neural":[65],"network":[66],"(DNN).":[67],"With":[68],"these":[69,117],"masks,":[70],"calculate":[75],"spatial":[77],"covariance":[78],"matrix":[79],"noise":[81,98],"steering":[83],"vector":[84],"beamforming.":[86,103],"In":[87],"addition,":[88],"post-filter":[93],"further":[95],"suppress":[96],"output":[101],"Then,":[104],"enhanced":[106,129],"is":[108,134],"sent":[109],"back":[110],"DNN":[112],"re-estimation.":[115],"When":[116],"steps":[118],"iterated":[120],"few":[123],"times,":[124],"obtain":[126],"final":[128],"proposed":[132],"evaluated":[135],"frontend":[138],"automatic":[140],"recognition":[142],"(ASR)":[143],"achieves":[145],"5.05%":[147],"average":[148],"word":[149],"error":[150],"rate":[151],"(WER)":[152],"real":[155],"environment":[156],"test":[157],"set":[158],"CHiME-3,":[160],"outperforming":[161],"current":[163],"best":[164],"by":[166],"13.34%.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
