{"id":"https://openalex.org/W2904310189","doi":"https://doi.org/10.1109/taslp.2018.2886739","title":"Mixed-Bandwidth Cross-Channel Speech Recognition via Joint Optimization of DNN-Based Bandwidth Expansion and Acoustic Modeling","display_name":"Mixed-Bandwidth Cross-Channel Speech Recognition via Joint Optimization of DNN-Based Bandwidth Expansion and Acoustic Modeling","publication_year":2018,"publication_date":"2018-12-13","ids":{"openalex":"https://openalex.org/W2904310189","doi":"https://doi.org/10.1109/taslp.2018.2886739","mag":"2904310189"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2886739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2886739","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"],"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/A5020540834","display_name":"Jianqing Gao","orcid":"https://orcid.org/0000-0001-5575-4940"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqing Gao","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5575-4940","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.1201,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84537247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"27","issue":"3","first_page":"559","last_page":"571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7735550403594971},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6976296305656433},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6361610889434814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5664120316505432},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.5249633193016052},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5178504586219788},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4561128616333008},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.4425141513347626},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.4313907325267792},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37122589349746704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35708528757095337},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3190869987010956},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.236487478017807},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.1200600266456604},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10432365536689758},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07872000336647034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735550403594971},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6976296305656433},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6361610889434814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5664120316505432},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.5249633193016052},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5178504586219788},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4561128616333008},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.4425141513347626},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.4313907325267792},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37122589349746704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35708528757095337},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3190869987010956},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.236487478017807},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.1200600266456604},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10432365536689758},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07872000336647034},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2886739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2886739","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G573022218","display_name":null,"funder_award_id":"U1613211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8173470123","display_name":"\u57fa\u4e8e\u56de\u5f52\u795e\u7ecf\u7f51\u7edc\u7684\u8bed\u97f3\u5206\u79bb\u5173\u952e\u95ee\u9898\u7814\u7a76","funder_award_id":"61671422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W1578856370","https://openalex.org/W1598508708","https://openalex.org/W1734538896","https://openalex.org/W1923007241","https://openalex.org/W1971868317","https://openalex.org/W1985819805","https://openalex.org/W1993882792","https://openalex.org/W1994997782","https://openalex.org/W2013598660","https://openalex.org/W2042141988","https://openalex.org/W2047481787","https://openalex.org/W2078528584","https://openalex.org/W2087402357","https://openalex.org/W2093866254","https://openalex.org/W2121290804","https://openalex.org/W2124173482","https://openalex.org/W2125964738","https://openalex.org/W2131342762","https://openalex.org/W2132462584","https://openalex.org/W2133856945","https://openalex.org/W2135567392","https://openalex.org/W2136922672","https://openalex.org/W2147152002","https://openalex.org/W2151643194","https://openalex.org/W2158843472","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2170292577","https://openalex.org/W2184045248","https://openalex.org/W2293634267","https://openalex.org/W2296073425","https://openalex.org/W2394932179","https://openalex.org/W2397254463","https://openalex.org/W2399004239","https://openalex.org/W2399742709","https://openalex.org/W2400830530","https://openalex.org/W2426267443","https://openalex.org/W2516547830","https://openalex.org/W2550246519","https://openalex.org/W2889905534","https://openalex.org/W2892335023","https://openalex.org/W2916986993","https://openalex.org/W2963490782","https://openalex.org/W4319988532","https://openalex.org/W6678367718","https://openalex.org/W6679966330","https://openalex.org/W6682013673","https://openalex.org/W6682565983","https://openalex.org/W6696934422","https://openalex.org/W6711962127","https://openalex.org/W6712300757","https://openalex.org/W6712508993","https://openalex.org/W6712911448","https://openalex.org/W6713030564","https://openalex.org/W6726061053","https://openalex.org/W6729491343","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W1964845213","https://openalex.org/W2599854282","https://openalex.org/W2164218571","https://openalex.org/W3107813721","https://openalex.org/W2135812553","https://openalex.org/W2017913521","https://openalex.org/W2040901912","https://openalex.org/W2403497193","https://openalex.org/W2152250293","https://openalex.org/W2025340797"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,11,41,90,112,122,187,265],"recognition":[2],"(ASR)":[3],"systems":[4],"are":[5,106,128,274],"often":[6],"built":[7],"using":[8,207],"scene":[9],"related":[10],"data":[12,42,266],"due":[13],"to":[14,65,81,88,146,164,276,288],"large":[15,68],"variations":[16],"of":[17,55,70,100,154,252],"transmission":[18],"channels":[19,192],"and":[20,47,62,94,193,198,218,238,283],"sampling":[21,45,144,149,194,232],"rates":[22,46,145,195],"in":[23,162],"different":[24,44,190,280],"scenarios.":[25],"In":[26],"this":[27],"study,":[28],"we":[29,75,169],"propose":[30],"a":[31,36,52,67,215,230,289],"general":[32],"framework":[33,50],"that":[34,202,255],"establishes":[35],"unified":[37,205],"model":[38,206,258],"for":[39,175,209,229],"diversified":[40,71,184,263],"with":[43,113,123,189,226,244,267],"channels.":[48],"The":[49,97],"is":[51,214],"joint":[53,172],"optimization":[54],"deep":[56],"neural":[57],"network":[58,135],"(DNN)-based":[59],"bandwidth":[60,166,210,228],"expansion":[61,167,211],"acoustic":[63,84,108,119,177,224],"modeling":[64],"exploit":[66],"amount":[69],"training":[72,173],"data.":[73],"First,":[74],"design":[76,153,220],"two":[77],"novel":[78],"DNN":[79,104],"architectures":[80],"map":[82],"the":[83,101,107,114,118,125,139,142,147,152,203,256,262,271],"features":[85,109,120,140],"from":[86,111,121,141],"narrowband":[87],"wideband":[89],"through":[91,151],"direct":[92,102],"mapping":[93,103],"progressive":[95,133],"mapping.":[96],"learning":[98],"targets":[99],"(DNN-DM)":[105],"extracted":[110],"largest":[115],"bandwidth,":[116],"while":[117],"all":[124],"other":[126],"bandwidths":[127],"used":[129],"as":[130],"input.":[131],"A":[132],"stacking":[134],"(PSN)":[136],"gradually":[137],"maps":[138],"low":[143],"highest":[148],"rate":[150,250],"intermediate":[155],"target":[156],"layers":[157],"via":[158],"multitask":[159],"training.":[160],"Then,":[161],"addition":[163],"these":[165],"networks,":[168],"investigate":[170],"several":[171],"strategies":[174],"DNN-based":[176],"models.":[178],"Our":[179],"experiments":[180],"conducted":[181],"on":[182,279],"three":[183],"large-scale":[185],"Mandarin":[186],"datasets":[188],"recording":[191],"(6,":[196],"8,":[197],"16":[199],"kHz)":[200],"show":[201],"proposed":[204,257,272],"PSN":[208],"not":[212],"only":[213],"more":[216],"flexible":[217],"compact":[219],"than":[221],"conventional":[222],"multiple":[223,268],"models":[225,243],"each":[227],"specific":[231],"rate,":[233],"but":[234],"also":[235],"yields":[236],"consistent":[237],"significant":[239],"improvements":[240],"over":[241],"bandwidth-dependent":[242],"an":[245],"average":[246],"relative":[247],"word":[248],"error":[249],"reduction":[251],"6.2%,":[253],"indicating":[254],"can":[259,284],"fully":[260],"utilize":[261],"cross-channel":[264],"bandwidths.":[269],"Moreover,":[270],"methods":[273],"verified":[275],"be":[277,285],"robust":[278],"realistic":[281],"scenes":[282],"effectively":[286],"extended":[287],"long":[290],"short-term":[291],"memory":[292],"framework.":[293]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}