{"id":"https://openalex.org/W3034443407","doi":"https://doi.org/10.1109/icme46284.2020.9102916","title":"Speech Intelligibility Enhancement Using Non-Parallel Speaking Style Conversion With Stargan And Dynamic Range Compression","display_name":"Speech Intelligibility Enhancement Using Non-Parallel Speaking Style Conversion With Stargan And Dynamic Range Compression","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3034443407","doi":"https://doi.org/10.1109/icme46284.2020.9102916","mag":"3034443407"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102916","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/A5100438653","display_name":"Gang Li","orcid":"https://orcid.org/0000-0001-9585-1382"},"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/A5008406199","display_name":"Ruimin Hu","orcid":"https://orcid.org/0000-0002-5872-3872"},"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/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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422092","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-8132-6250"},"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":"Rui Zhang","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":"last","author":{"id":"https://openalex.org/A5072984216","display_name":"Li Gao","orcid":"https://orcid.org/0000-0002-5918-3505"},"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":"Li Gao","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":6,"corresponding_author_ids":["https://openalex.org/A5100438653"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65813035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9926000237464905,"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":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805795669555664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7191080451011658},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.658319890499115},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6284410357475281},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5691343545913696},{"id":"https://openalex.org/keywords/dynamic-range-compression","display_name":"Dynamic range compression","score":0.5236544609069824},{"id":"https://openalex.org/keywords/dynamic-range","display_name":"Dynamic range","score":0.4137764573097229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31246960163116455},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27805155515670776},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14165785908699036},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11133119463920593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805795669555664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7191080451011658},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.658319890499115},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6284410357475281},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5691343545913696},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.5236544609069824},{"id":"https://openalex.org/C87133666","wikidata":"https://www.wikidata.org/wiki/Q1161699","display_name":"Dynamic range","level":2,"score":0.4137764573097229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31246960163116455},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27805155515670776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14165785908699036},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11133119463920593},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme46284.2020.9102916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102916","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":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2006584300","https://openalex.org/W2048653958","https://openalex.org/W2080534788","https://openalex.org/W2084458166","https://openalex.org/W2084636655","https://openalex.org/W2123771434","https://openalex.org/W2152205330","https://openalex.org/W2398850442","https://openalex.org/W2471520273","https://openalex.org/W2747057337","https://openalex.org/W2750452568","https://openalex.org/W2810311710","https://openalex.org/W2936173958","https://openalex.org/W2962793481","https://openalex.org/W2963767194","https://openalex.org/W2964341837","https://openalex.org/W2972497784","https://openalex.org/W3103318788","https://openalex.org/W4293398859","https://openalex.org/W6730095352","https://openalex.org/W6761245657"],"related_works":["https://openalex.org/W2085637247","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/W3114966213","https://openalex.org/W1964261467","https://openalex.org/W4306405983"],"abstract_inverted_index":{"Speech":[0],"intelligibility":[1,32],"enhancement":[2,6,110],"is":[3,16,39],"a":[4,40,45,92,98,108],"perceptual":[5],"technique":[7],"for":[8],"clean":[9],"speech":[10,31,85],"reproduced":[11],"in":[12,19,78,117,126],"noisy":[13],"environments.":[14],"It":[15,68],"typically":[17],"used":[18],"the":[20,113,118,123],"listening":[21],"stage":[22],"of":[23,87,115],"multimedia":[24],"communications.":[25],"In":[26],"this":[27],"study,":[28],"we":[29,106],"enhance":[30],"by":[33,44],"speaking":[34],"style":[35],"conversion":[36,77,94],"(SSC),":[37],"which":[38,121],"data-driven":[41],"approach":[42],"inspired":[43],"vocal":[46],"mechanism":[47],"named":[48],"Lombard":[49],"effect.":[50],"The":[51],"proposed":[52],"SSC":[53,124],"method":[54,134],"combines":[55],"star":[56],"generative":[57],"adversarial":[58],"network":[59],"(StarGAN)":[60],"based":[61],"mapping":[62],"and":[63,101],"dynamic":[64],"range":[65],"compression":[66],"(DRC).":[67],"has":[69],"two":[70],"main":[71],"advantages:":[72],"1)":[73],"different":[74,88],"from":[75],"gender-independent":[76],"previous":[79],"studies,":[80],"StarGAN":[81,119],"can":[82],"separately":[83],"learn":[84],"features":[86],"genders":[89,96],"to":[90],"provide":[91],"differential":[93],"among":[95],"with":[97,112],"single":[99],"model":[100],"non-parallel":[102],"training":[103],"data;":[104],"2)":[105],"design":[107],"multi-level":[109],"strategy":[111],"use":[114],"DRC":[116],"architecture,":[120],"improves":[122],"performance":[125],"strong":[127],"noise":[128],"interference.":[129],"Experiments":[130],"show":[131],"that":[132],"our":[133],"outperforms":[135],"baseline":[136],"methods.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}