{"id":"https://openalex.org/W3163838801","doi":"https://doi.org/10.1109/icassp39728.2021.9414346","title":"Real-Time Speech Enhancement for Mobile Communication Based on Dual-Channel Complex Spectral Mapping","display_name":"Real-Time Speech Enhancement for Mobile Communication Based on Dual-Channel Complex Spectral Mapping","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163838801","doi":"https://doi.org/10.1109/icassp39728.2021.9414346","mag":"3163838801"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5058209019","display_name":"Ke Tan","orcid":"https://orcid.org/0000-0001-5073-8060"},"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":"Ke Tan","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","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":["Inner Mongolia University,Department of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Department of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]}]},{"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":["The Ohio State University,Department of Computer Science and Engineering,USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6134","last_page":"6138"},"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":0.995199978351593,"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":0.9914000034332275,"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-enhancement","display_name":"Speech enhancement","score":0.832399845123291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7680110931396484},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5914285182952881},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5412340760231018},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5406519770622253},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5170560479164124},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4818743169307709},{"id":"https://openalex.org/keywords/mobile-telephony","display_name":"Mobile telephony","score":0.472053587436676},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46571114659309387},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4627414345741272},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43225717544555664},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4314475655555725},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3974984288215637},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.29495200514793396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2222316563129425},{"id":"https://openalex.org/keywords/mobile-radio","display_name":"Mobile radio","score":0.20686963200569153},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1435469090938568}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.832399845123291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680110931396484},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5914285182952881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5412340760231018},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5406519770622253},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5170560479164124},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4818743169307709},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.472053587436676},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46571114659309387},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4627414345741272},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43225717544555664},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4314475655555725},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3974984288215637},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.29495200514793396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2222316563129425},{"id":"https://openalex.org/C2781307350","wikidata":"https://www.wikidata.org/wiki/Q6887221","display_name":"Mobile radio","level":2,"score":0.20686963200569153},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1435469090938568},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W20506061","https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W2028929783","https://openalex.org/W2044214142","https://openalex.org/W2100417866","https://openalex.org/W2117678320","https://openalex.org/W2124575599","https://openalex.org/W2141998673","https://openalex.org/W2291877678","https://openalex.org/W2460144244","https://openalex.org/W2548509518","https://openalex.org/W2567070169","https://openalex.org/W2599685671","https://openalex.org/W2734957715","https://openalex.org/W2774389566","https://openalex.org/W2785523195","https://openalex.org/W2799339656","https://openalex.org/W2803417661","https://openalex.org/W2884436604","https://openalex.org/W2889442120","https://openalex.org/W2937525188","https://openalex.org/W2963970792","https://openalex.org/W2991361823","https://openalex.org/W3015679215","https://openalex.org/W6629014544","https://openalex.org/W6675550164","https://openalex.org/W6731370813","https://openalex.org/W6740873641","https://openalex.org/W6747620207","https://openalex.org/W6761887639","https://openalex.org/W6774803370"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W2380771148","https://openalex.org/W1505346162","https://openalex.org/W2348931051","https://openalex.org/W4200562864","https://openalex.org/W2120771489","https://openalex.org/W2538903081"],"abstract_inverted_index":{"Speech":[0],"quality":[1],"and":[2,29],"intelligibility":[3],"can":[4],"be":[5],"severely":[6],"degraded":[7],"by":[8],"back-ground":[9,18],"noise":[10],"in":[11],"mobile":[12,27,53,116],"communication.":[13,117],"In":[14],"order":[15],"to":[16,36,47,64,88,111],"attenuate":[17],"noise,":[19],"speech":[20,49,113],"enhancement":[21,39,50,84,91,114],"systems":[22],"have":[23],"been":[24],"integrated":[25],"into":[26],"phones,":[28],"a":[30,44,58,72,89],"microphone":[31],"array":[32],"is":[33],"typically":[34],"deployed":[35],"improve":[37],"the":[38,78,83,100,105],"performance.":[40,85],"This":[41,86],"paper":[42],"proposes":[43],"novel":[45],"approach":[46,56,102,110],"real-time":[48,90],"for":[51,76,93,115],"dual-microphone":[52],"phones.":[54],"Our":[55],"employs":[57],"causal":[59],"densely-connected":[60],"convolutional":[61],"recurrent":[62],"network":[63],"perform":[65],"dual-channel":[66,112],"complex":[67],"spectral":[68],"mapping.":[69],"We":[70],"apply":[71],"structured":[73],"pruning":[74],"technique":[75],"compressing":[77],"model":[79],"without":[80],"significantly":[81],"affecting":[82],"leads":[87],"system":[92],"on-device":[94],"processing.":[95],"Evaluation":[96],"results":[97],"show":[98],"that":[99],"pro-posed":[101],"substantially":[103],"advances":[104],"performance":[106],"of":[107],"an":[108],"earlier":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
