{"id":"https://openalex.org/W2550246519","doi":"https://doi.org/10.1109/ijcnn.2016.7727253","title":"An experimental study on joint modeling of mixed-bandwidth data via deep neural networks for robust speech recognition","display_name":"An experimental study on joint modeling of mixed-bandwidth data via deep neural networks for robust speech recognition","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2550246519","doi":"https://doi.org/10.1109/ijcnn.2016.7727253","mag":"2550246519"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2016.7727253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5067283726","display_name":"Jianqing Gao","orcid":null},"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":true,"raw_author_name":"Jianqing Gao","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. 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 of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042701682","display_name":"Changqing Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changqing Kong","raw_affiliation_strings":["iFlytek Research, iFlytek Co., Ltd, Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd, Hefei, Anhui, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100984887","display_name":"Huaifang Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaifang Lu","raw_affiliation_strings":["iFlytek Research, iFlytek Co., Ltd, Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd, Hefei, Anhui, P. R. China","institution_ids":[]}]},{"author_position":"middle","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 of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067283726"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.9993,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92991677,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"588","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/narrowband","display_name":"Narrowband","score":0.924231767654419},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.8203824758529663},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.7820000648498535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7785391807556152},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.733970582485199},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6337102651596069},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5182740092277527},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4526486396789551},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45160236954689026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.378355473279953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32780951261520386},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2702614665031433},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.15854117274284363},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14267563819885254},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10382211208343506},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.060326188802719116}],"concepts":[{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.924231767654419},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.8203824758529663},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.7820000648498535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785391807556152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.733970582485199},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6337102651596069},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5182740092277527},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4526486396789551},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45160236954689026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.378355473279953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32780951261520386},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2702614665031433},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.15854117274284363},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14267563819885254},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10382211208343506},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.060326188802719116},{"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/ijcnn.2016.7727253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W1522137499","https://openalex.org/W1586176709","https://openalex.org/W1598508708","https://openalex.org/W1932968309","https://openalex.org/W1971868317","https://openalex.org/W1985819805","https://openalex.org/W1994997782","https://openalex.org/W2013598660","https://openalex.org/W2042141988","https://openalex.org/W2078528584","https://openalex.org/W2087402357","https://openalex.org/W2132462584","https://openalex.org/W2133856945","https://openalex.org/W2135567392","https://openalex.org/W2136922672","https://openalex.org/W2147152002","https://openalex.org/W2158843472","https://openalex.org/W2397254463","https://openalex.org/W2399004239","https://openalex.org/W2399742709","https://openalex.org/W2400830530","https://openalex.org/W2408713104","https://openalex.org/W6682013673","https://openalex.org/W6712300757","https://openalex.org/W6712508993","https://openalex.org/W6712911448","https://openalex.org/W6713030564","https://openalex.org/W6713729801"],"related_works":["https://openalex.org/W1964845213","https://openalex.org/W2599854282","https://openalex.org/W3107813721","https://openalex.org/W2135812553","https://openalex.org/W2017913521","https://openalex.org/W2315098011","https://openalex.org/W2114570682","https://openalex.org/W2040901912","https://openalex.org/W2403497193","https://openalex.org/W2098618660"],"abstract_inverted_index":{"We":[0,25,39],"propose":[1],"joint":[2,97],"modeling":[3,98],"strategies":[4,136],"leveraging":[5],"upon":[6],"large-scale":[7],"mixed-band":[8,100],"training":[9],"speech":[10,43,88,101,112],"for":[11,96],"recognition":[12,89],"of":[13,70,99,123],"both":[14,107],"narrowband":[15,35,53,59,109,128],"and":[16,29,36,60,72,75,110,125,129],"wideband":[17,37,55,61,111,130],"data":[18],"based":[19],"on":[20,85,127],"deep":[21],"neural":[22],"networks":[23],"(DNNs).":[24],"utilize":[26],"conventional":[27,141],"down-sampling":[28,74],"up-sampling":[30,76],"schemes":[31],"to":[32,47,54],"go":[33],"between":[34],"data.":[38],"also":[40,137],"explore":[41],"DNN-based":[42,142],"bandwidth":[44],"expansion":[45],"(BWE)":[46],"map":[48],"some":[49],"acoustic":[50],"features":[51,62],"from":[52],"speech.":[56],"By":[57],"arranging":[58],"at":[63],"the":[64,67,93,108,134],"input":[65],"or":[66],"output":[68],"level":[69],"BWE-DNN,":[71],"combining":[73],"data,":[77,131],"different":[78],"DNNs":[79,95],"can":[80],"be":[81],"established.":[82],"Our":[83],"experiments":[84],"a":[86,117],"Mandarin":[87],"task":[90],"show":[91],"that":[92],"hybrid":[94],"yield":[102],"significant":[103],"performance":[104],"gains":[105],"over":[106],"models,":[113],"well-trained":[114],"separately,":[115],"with":[116],"relative":[118],"character":[119],"error":[120],"rate":[121],"reduction":[122],"7.9%":[124],"3.9%":[126],"respectively.":[132],"Furthermore,":[133],"proposed":[135],"consistently":[138],"outperform":[139],"other":[140],"methods.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}