{"id":"https://openalex.org/W3035123403","doi":"https://doi.org/10.1109/icme46284.2020.9102857","title":"Normal-To-Lombard Speech Conversion by LSTM Network and BGMM for Intelligibility Enhancement of Telephone Speech","display_name":"Normal-To-Lombard Speech Conversion by LSTM Network and BGMM for Intelligibility Enhancement of Telephone Speech","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3035123403","doi":"https://doi.org/10.1109/icme46284.2020.9102857","mag":"3035123403"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","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/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":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, 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"]}],"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, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","institution_ids":["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":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, 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, China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Wuhan University in 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, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, 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":0.6061,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65878868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"s3 5 1997","issue":null,"first_page":"1","last_page":"6"},"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":0.9990000128746033,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8388519287109375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7853420376777649},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7472355365753174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401473522186279},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5936842560768127},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.467048317193985},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.46398189663887024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32069623470306396},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27663862705230713}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8388519287109375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7853420376777649},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7472355365753174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401473522186279},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5936842560768127},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.467048317193985},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.46398189663887024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32069623470306396},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27663862705230713},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme46284.2020.9102857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W65497148","https://openalex.org/W2006584300","https://openalex.org/W2048653958","https://openalex.org/W2084636655","https://openalex.org/W2119500623","https://openalex.org/W2139862710","https://openalex.org/W2149948223","https://openalex.org/W2398850442","https://openalex.org/W2471520273","https://openalex.org/W2576309025","https://openalex.org/W2594639291","https://openalex.org/W2604542730","https://openalex.org/W2747057337","https://openalex.org/W2747120924","https://openalex.org/W2748191214","https://openalex.org/W2810311710","https://openalex.org/W2911412811","https://openalex.org/W2972497784","https://openalex.org/W4234195863"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484"],"abstract_inverted_index":{"Noise":[0],"in":[1,37,101],"the":[2,6,17,19,62,73,94],"environment":[3],"significantly":[4],"decreases":[5],"speech":[7,14,36,44,63,77],"intelligibility":[8,31],"of":[9,34,76,89],"telephone":[10,35],"conversations.":[11],"Despite":[12],"clean":[13],"output":[15],"from":[16],"device,":[18],"listener":[20],"is":[21],"still":[22],"hard":[23],"to":[24,60],"get":[25],"information.":[26],"This":[27],"study":[28],"focuses":[29],"on":[30,42],"enhancement":[32],"(IENH)":[33],"near-end":[38],"background":[39],"noise":[40],"based":[41],"normal-to-Lombard":[43],"conversion.":[45],"The":[46],"proposed":[47,95],"approach":[48,96],"uses":[49],"long":[50],"short-term":[51,74],"memory":[52],"(LSTM)":[53],"and":[54,78,86,104],"Bayesian":[55],"Gaussian":[56],"mixture":[57],"model":[58],"(BGMM)":[59],"build":[61],"mapping":[64],"model.":[65],"Compared":[66],"with":[67,82],"previous":[68],"studies,":[69],"we":[70],"fully":[71],"consider":[72],"correlations":[75],"implement":[79],"feature":[80],"mappings":[81],"higher":[83],"dimensional":[84],"features":[85],"more":[87],"types":[88],"features.":[90],"Evaluations":[91],"indicate":[92],"that":[93],"has":[97],"achieved":[98],"better":[99],"results":[100],"both":[102],"objective":[103],"subjective":[105],"evaluation.":[106]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}