{"id":"https://openalex.org/W3165227983","doi":"https://doi.org/10.1109/taslp.2021.3082318","title":"Deep Learning Based Real-Time Speech Enhancement for Dual-Microphone Mobile Phones","display_name":"Deep Learning Based Real-Time Speech Enhancement for Dual-Microphone Mobile Phones","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3165227983","doi":"https://doi.org/10.1109/taslp.2021.3082318","mag":"3165227983","pmid":"https://pubmed.ncbi.nlm.nih.gov/34179221"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3082318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082318","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8224499","any_repository_has_fulltext":true},"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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 43210-1277 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-5073-8060","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 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":["Department of Computer Science, Inner Mongolia University, Hohhot 010021, China","Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-0406-1105","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot 010021, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, 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":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277, USA","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, 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":5.2401,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96503788,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1853","last_page":"1863"},"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":0.9959999918937683,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/computer-science","display_name":"Computer science","score":0.8064211010932922},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.799569845199585},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6492637991905212},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5892845392227173},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.577168881893158},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5553146600723267},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5489802360534668},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4645763337612152},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4513498842716217},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4506079852581024},{"id":"https://openalex.org/keywords/mobile-phone","display_name":"Mobile phone","score":0.43261200189590454},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4131767749786377},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4067418575286865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34715378284454346},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2660664916038513},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09996739029884338},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0744813084602356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064211010932922},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.799569845199585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6492637991905212},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5892845392227173},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.577168881893158},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5553146600723267},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5489802360534668},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4645763337612152},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4513498842716217},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4506079852581024},{"id":"https://openalex.org/C2777421447","wikidata":"https://www.wikidata.org/wiki/Q17517","display_name":"Mobile phone","level":2,"score":0.43261200189590454},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4131767749786377},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4067418575286865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34715378284454346},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2660664916038513},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09996739029884338},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0744813084602356},{"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/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},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2021.3082318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082318","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:34179221","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34179221","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8224499","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8224499","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8224499","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8224499","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W20506061","https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1987371344","https://openalex.org/W2028929783","https://openalex.org/W2044214142","https://openalex.org/W2048142341","https://openalex.org/W2060108923","https://openalex.org/W2069681747","https://openalex.org/W2100417866","https://openalex.org/W2117678320","https://openalex.org/W2124575599","https://openalex.org/W2141998673","https://openalex.org/W2288576889","https://openalex.org/W2291877678","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2460144244","https://openalex.org/W2548509518","https://openalex.org/W2561557072","https://openalex.org/W2567070169","https://openalex.org/W2599685671","https://openalex.org/W2718052359","https://openalex.org/W2734957715","https://openalex.org/W2736953746","https://openalex.org/W2771725120","https://openalex.org/W2774389566","https://openalex.org/W2785523195","https://openalex.org/W2799339656","https://openalex.org/W2803417661","https://openalex.org/W2884436604","https://openalex.org/W2888186106","https://openalex.org/W2889411318","https://openalex.org/W2889442120","https://openalex.org/W2897371647","https://openalex.org/W2937525188","https://openalex.org/W2962866211","https://openalex.org/W2963285578","https://openalex.org/W2963970792","https://openalex.org/W2991361823","https://openalex.org/W3015197852","https://openalex.org/W3015219411","https://openalex.org/W3015679215","https://openalex.org/W4231807801","https://openalex.org/W6638667902","https://openalex.org/W6685562342","https://openalex.org/W6731370813","https://openalex.org/W6740873641","https://openalex.org/W6747620207","https://openalex.org/W6753182481"],"related_works":["https://openalex.org/W2380771148","https://openalex.org/W2348931051","https://openalex.org/W2132495960","https://openalex.org/W2120771489","https://openalex.org/W2538903081","https://openalex.org/W2389562147","https://openalex.org/W2109356272","https://openalex.org/W4386746628","https://openalex.org/W2051376034","https://openalex.org/W2294333436"],"abstract_inverted_index":{"In":[0,44],"mobile":[1,34,61,123],"speech":[2,4,27,57,120],"communication,":[3,125],"signals":[5],"can":[6],"be":[7],"severely":[8],"corrupted":[9],"by":[10],"background":[11,25],"noise":[12],"when":[13],"the":[14,87,92,110],"far-end":[15],"talker":[16],"is":[17],"in":[18,36],"a":[19,49,67,81,97,129],"noisy":[20],"acoustic":[21],"environment.":[22],"To":[23],"suppress":[24],"noise,":[26],"enhancement":[28,58,93,101,121],"systems":[29],"are":[30,42],"typically":[31],"integrated":[32],"into":[33],"phones,":[35],"which":[37,95],"one":[38],"or":[39],"more":[40],"microphones":[41],"deployed.":[43],"this":[45],"study,":[46],"we":[47],"propose":[48],"novel":[50],"deep":[51,130],"learning":[52,131],"based":[53,132],"approach":[54,65,112,117],"to":[55,73,85,118],"real-time":[56,104],"for":[59,103,122],"dual-microphone":[60],"phones.":[62],"The":[63],"proposed":[64,111],"employs":[66],"new":[68],"densely-connected":[69],"convolutional":[70],"recurrent":[71],"network":[72],"perform":[74],"dual-channel":[75,119],"complex":[76],"spectral":[77],"mapping.":[78],"We":[79],"utilize":[80],"structured":[82],"pruning":[83],"technique":[84],"compress":[86],"model":[88],"without":[89],"significantly":[90],"degrading":[91],"performance,":[94],"yields":[96],"low-latency":[98],"and":[99],"memory-efficient":[100],"system":[102],"processing.":[105],"Experimental":[106],"results":[107],"suggest":[108],"that":[109],"consistently":[113],"outperforms":[114],"an":[115],"earlier":[116],"phone":[124],"as":[126,128],"well":[127],"beamformer.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
