{"id":"https://openalex.org/W3148935696","doi":"https://doi.org/10.1109/tmm.2021.3068565","title":"Intelligibility Enhancement Via Normal-to-Lombard Speech Conversion With Long Short-Term Memory Network and Bayesian Gaussian Mixture Model","display_name":"Intelligibility Enhancement Via Normal-to-Lombard Speech Conversion With Long Short-Term Memory Network and Bayesian Gaussian Mixture Model","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3148935696","doi":"https://doi.org/10.1109/tmm.2021.3068565","mag":"3148935696"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3068565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3068565","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","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/A5100636685","display_name":"Gang Li","orcid":"https://orcid.org/0000-0001-8368-0125"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Li","raw_affiliation_strings":["Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401931","display_name":"Xiaochen Wang","orcid":"https://orcid.org/0000-0003-4177-7580"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochen Wang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","Research Institute of Wuhan University in Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Research Institute of Wuhan University in Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210105229","https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087726516","display_name":"Ruimin Hu","orcid":"https://orcid.org/0000-0002-0290-5757"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Hu","raw_affiliation_strings":["Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053880803","display_name":"Huyin Zhang","orcid":"https://orcid.org/0000-0003-3820-3586"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huyin Zhang","raw_affiliation_strings":["Research Institute of Wuhan University in Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Wuhan University in Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210105229","https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044380704","display_name":"Shanfa Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanfa Ke","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100636685"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.6094,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6505071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":null,"first_page":"3035","last_page":"3047"},"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":0.9977999925613403,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7304979562759399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638941168785095},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6537154316902161},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6128618717193604},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4965363144874573},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4230199158191681},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.41136419773101807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30128175020217896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17818188667297363}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7304979562759399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638941168785095},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6537154316902161},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6128618717193604},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4965363144874573},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4230199158191681},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.41136419773101807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30128175020217896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17818188667297363},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3068565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3068565","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G3242532954","display_name":null,"funder_award_id":"2017YFB1002803","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G8285155503","display_name":null,"funder_award_id":"61801334","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"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W65497148","https://openalex.org/W1604034532","https://openalex.org/W1663973292","https://openalex.org/W1971876942","https://openalex.org/W1974387177","https://openalex.org/W2006584300","https://openalex.org/W2008291900","https://openalex.org/W2012086895","https://openalex.org/W2033321754","https://openalex.org/W2048653958","https://openalex.org/W2049686551","https://openalex.org/W2056116740","https://openalex.org/W2063125572","https://openalex.org/W2064675550","https://openalex.org/W2066754815","https://openalex.org/W2075076415","https://openalex.org/W2080534788","https://openalex.org/W2084636655","https://openalex.org/W2093450784","https://openalex.org/W2103442919","https://openalex.org/W2109720703","https://openalex.org/W2118638413","https://openalex.org/W2119500623","https://openalex.org/W2139862710","https://openalex.org/W2149948223","https://openalex.org/W2398850442","https://openalex.org/W2404548911","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2519648275","https://openalex.org/W2576309025","https://openalex.org/W2604542730","https://openalex.org/W2747057337","https://openalex.org/W2747070883","https://openalex.org/W2747120924","https://openalex.org/W2748191214","https://openalex.org/W2749552851","https://openalex.org/W2750452568","https://openalex.org/W2810311710","https://openalex.org/W2911412811","https://openalex.org/W2936173958","https://openalex.org/W2949382160","https://openalex.org/W2972497784","https://openalex.org/W3035123403","https://openalex.org/W3103318788","https://openalex.org/W3103840368","https://openalex.org/W3209184074","https://openalex.org/W4212863985","https://openalex.org/W4231942877","https://openalex.org/W4234195863"],"related_works":["https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W2366328218","https://openalex.org/W2509366663","https://openalex.org/W2085637247","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Speech":[0],"communications":[1],"and":[2,21,99,133,162,178,197],"interactions":[3],"frequently":[4],"occur":[5],"in":[6,12,24,58,194],"a":[7,51,64,81,107,155],"variety":[8],"of":[9,48,67,165],"environments.":[10],"Noise":[11],"the":[13,25,30,55,59,87,93,138,145,163,168],"environment":[14],"significantly":[15],"degrades":[16],"speech":[17,49,77],"intelligibility":[18],"when":[19],"speaking":[20],"listening.":[22],"Especially":[23],"listening":[26,60],"stage,":[27],"even":[28],"if":[29],"multimedia":[31],"terminal":[32],"outputs":[33],"clean":[34],"speech,":[35],"it":[36,113],"is":[37,50,122,141,171],"still":[38],"difficult":[39],"for":[40,53,124,173],"listeners":[41],"to":[42,105,180],"obtain":[43],"information.":[44],"Intelligibility":[45],"enhancement":[46,66],"(IENH)":[47],"technique":[52],"overcoming":[54],"environmental":[56],"noise":[57],"stage.":[61],"It":[62],"implements":[63],"perceptual":[65],"non-noisy":[68],"speech.":[69],"This":[70],"study":[71],"focuses":[72],"on":[73],"IENH":[74],"via":[75],"normal-to-Lombard":[76],"conversion,":[78],"inspired":[79],"by":[80,154],"well":[82],"known":[83],"acoustic":[84],"mechanism":[85],"named":[86],"Lombard":[88],"effect.":[89],"Our":[90],"method":[91,190],"combines":[92],"long":[94],"short-term":[95,131],"memory":[96],"(LSTM)":[97],"network":[98,121],"Bayesian":[100],"Gaussian":[101],"mixture":[102],"model":[103],"(BGMM)":[104],"build":[106],"conversion":[108],"architecture.":[109],"Compared":[110],"with":[111,128,144],"baselines,":[112],"has":[114],"three":[115],"main":[116],"advantages:":[117],"1)":[118],"an":[119],"LSTM":[120],"used":[123,172],"spectral":[125],"tilt":[126],"mapping":[127,170],"fully":[129],"considering":[130],"correlations":[132],"high-dimensional":[134],"expression":[135],"abilities;":[136],"2)":[137],"aperiodicity":[139],"(AP)":[140],"mapped":[142],"together":[143],"fundamental":[146],"frequency":[147],"(":[148],"<inline-formula":[149,174],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150,175],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[151,176],"notation=\"LaTeX\">$F_0$</tex-math></inline-formula>":[152,177],")":[153],"BGMM,":[156],"which":[157],"considers":[158],"their":[159],"relevance":[160],"constraints":[161],"importance":[164],"APs;":[166],"3)":[167],"gender-dependent":[169],"APs":[179],"consider":[181],"distribution":[182],"differences":[183],"between":[184],"genders.":[185],"Experiments":[186],"indicate":[187],"that":[188],"our":[189],"gets":[191],"better":[192],"performance":[193],"both":[195],"objective":[196],"subjective":[198],"tests.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}