{"id":"https://openalex.org/W2785712565","doi":"https://doi.org/10.1109/icassp.2018.8462042","title":"Constrained Convolutional-Recurrent Networks to Improve Speech Quality with Low Impact on Recognition Accuracy","display_name":"Constrained Convolutional-Recurrent Networks to Improve Speech Quality with Low Impact on Recognition Accuracy","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2785712565","doi":"https://doi.org/10.1109/icassp.2018.8462042","mag":"2785712565"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.05874","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010753342","display_name":"Rasool Fakoor","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rasool Fakoor","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Univ. of Texas, Arlington, TX","Department of Computer Science and Engineering, University of Texas, Arlington, TX 76019"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Univ. of Texas, Arlington, TX","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, TX 76019","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Univ. of Texas, Arlington, TX","Department of Computer Science and Engineering, University of Texas, Arlington, TX 76019"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Univ. of Texas, Arlington, TX","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, TX 76019","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft Research, Redmond, WA","Microsoft Research, Redmond, WA 98052;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052;","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084618329","display_name":"Shuayb Zarar","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuayb Zarar","raw_affiliation_strings":["Microsoft Research, Redmond, WA","Microsoft Research, Redmond, WA 98052;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052;","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9976,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75597993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3011","last_page":"3015"},"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":0.9973999857902527,"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":0.9965999722480774,"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/pesq","display_name":"PESQ","score":0.938877522945404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8457496762275696},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6802773475646973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6787968277931213},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5468149781227112},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5273928046226501},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5044506788253784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4983181953430176},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4820078909397125},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4537924826145172},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42156556248664856},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4110201597213745},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.291493684053421}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.938877522945404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457496762275696},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6802773475646973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6787968277931213},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5468149781227112},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5273928046226501},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5044506788253784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4983181953430176},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4820078909397125},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4537924826145172},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42156556248664856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4110201597213745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.291493684053421},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.05874","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.05874","pdf_url":"https://arxiv.org/pdf/1802.05874","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2785712565","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.05874v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1802.05874","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.05874","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.05874","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.05874","pdf_url":"https://arxiv.org/pdf/1802.05874","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2785712565.pdf","grobid_xml":"https://content.openalex.org/works/W2785712565.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2078528584","https://openalex.org/W2119717200","https://openalex.org/W2130942839","https://openalex.org/W2147768505","https://openalex.org/W2153897396","https://openalex.org/W2160815625","https://openalex.org/W2290318471","https://openalex.org/W2296073425","https://openalex.org/W2403766732","https://openalex.org/W2507424718","https://openalex.org/W2610674366","https://openalex.org/W2746659549","https://openalex.org/W2963840672","https://openalex.org/W2963853675","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6674385629","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6684191040","https://openalex.org/W6684205842","https://openalex.org/W6696085341","https://openalex.org/W6696830301","https://openalex.org/W6712909570","https://openalex.org/W6713298849","https://openalex.org/W6729759494","https://openalex.org/W6746059548"],"related_works":["https://openalex.org/W2963954250","https://openalex.org/W3088159194","https://openalex.org/W2994785103","https://openalex.org/W3199713199","https://openalex.org/W3164736513","https://openalex.org/W2797972631","https://openalex.org/W3206706278","https://openalex.org/W3095913803","https://openalex.org/W3003901600","https://openalex.org/W3160973314","https://openalex.org/W3048758284","https://openalex.org/W3005262054","https://openalex.org/W2749588430","https://openalex.org/W2965016789","https://openalex.org/W3031135612","https://openalex.org/W3027637851","https://openalex.org/W3168189696","https://openalex.org/W2755226751","https://openalex.org/W2809840276","https://openalex.org/W3186546663"],"abstract_inverted_index":{"For":[0],"a":[1,28,44,71,79],"speech-enhancement":[2],"algorithm,":[3],"it":[4,23],"is":[5,24],"highly":[6],"desirable":[7],"to":[8,17,26,121],"simultaneously":[9],"improve":[10],"perceptual":[11,63],"quality":[12],"and":[13,20,52,110,116],"recognition":[14,87],"rate.":[15,88],"Thanks":[16],"computational":[18],"costs":[19],"model":[21,29],"complexities,":[22],"challenging":[25],"train":[27],"that":[30,49,61,82,99],"effectively":[31],"optimizes":[32],"both":[33],"metrics":[34],"at":[35],"the":[36,66,75,84,122,126],"same":[37,67],"time.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,69,97],"propose":[43],"method":[45],"for":[46,105],"speech":[47,106],"enhancement":[48,107],"combines":[50],"local":[51],"global":[53],"contextual":[54],"structures":[55],"information":[56],"through":[57],"convolutional-recurrent":[58],"neural":[59],"networks":[60],"improves":[62,108],"quality.":[64],"At":[65],"time,":[68],"introduce":[70],"new":[72,101],"constraint":[73],"on":[74,86,90],"objective":[76],"function":[77],"using":[78],"language":[80],"model/decoder":[81],"limits":[83],"impact":[85],"Based":[89],"experiments":[91],"conducted":[92],"with":[93],"real":[94],"user":[95],"data,":[96],"demonstrate":[98],"our":[100],"context-augmented":[102],"machine-learning":[103],"approach":[104],"PESQ":[109],"WER":[111],"by":[112],"an":[113],"additional":[114],"24.5%":[115],"51.3%,":[117],"respectively,":[118],"when":[119],"compared":[120],"best-performing":[123],"methods":[124],"in":[125],"literature.":[127]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}