{"id":"https://openalex.org/W4295465383","doi":"https://doi.org/10.1109/embc48229.2022.9871247","title":"A Deep Learning Based Approach to Synthesize Intelligible Speech with Limited Temporal Envelope Information","display_name":"A Deep Learning Based Approach to Synthesize Intelligible Speech with Limited Temporal Envelope Information","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4295465383","doi":"https://doi.org/10.1109/embc48229.2022.9871247","pmid":"https://pubmed.ncbi.nlm.nih.gov/36086160"},"language":"en","primary_location":{"id":"doi:10.1109/embc48229.2022.9871247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc48229.2022.9871247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607706","display_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"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/A5036552349","display_name":"Ching-Ju Hsiao","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ching-Ju Hsiao","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Biomedical Engineering,Taipei,Taiwan","Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Biomedical Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405410","display_name":"Fei Chen","orcid":"https://orcid.org/0000-0002-6988-492X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Chen","raw_affiliation_strings":["Southern University of Science and Technology,Department of Electrical and Electronic Engineering,Shenzhen,China","Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Electrical and Electronic Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040816118","display_name":"Ji-Yan Han","orcid":"https://orcid.org/0000-0001-9208-8502"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ji-Yan Han","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Biomedical Engineering,Taipei,Taiwan","Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Biomedical Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112562051","display_name":"Wei-Zhong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Zhong Zheng","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Biomedical Engineering,Taipei,Taiwan","Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Biomedical Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027128278","display_name":"Ying-Hui Lai","orcid":"https://orcid.org/0000-0003-4120-7289"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Hui Lai","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Biomedical Engineering and Medical Device Innovation &#x0026; Translation Center,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Biomedical Engineering and Medical Device Innovation &#x0026; Translation Center,Taipei,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09515952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"521","issue":null,"first_page":"1972","last_page":"1976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.9004502296447754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7187954783439636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6719744205474854},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5188280940055847},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.50235915184021},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.48283228278160095},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.44889193773269653},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4312952756881714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42074882984161377},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12960654497146606}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.9004502296447754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7187954783439636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6719744205474854},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5188280940055847},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.50235915184021},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.48283228278160095},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.44889193773269653},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4312952756881714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42074882984161377},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12960654497146606},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001307","descriptor_name":"Auditory Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001307","descriptor_name":"Auditory Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001307","descriptor_name":"Auditory Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013065","descriptor_name":"Speech Intelligibility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013065","descriptor_name":"Speech Intelligibility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013065","descriptor_name":"Speech Intelligibility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc48229.2022.9871247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc48229.2022.9871247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607706","display_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:36086160","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36086160","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G550806178","display_name":"Speaking for dysarthria - Core corpus, AI voice conversion and clinical trials( II )","funder_award_id":"MOST110-2218-EA49A-501","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1664554799","https://openalex.org/W1899731913","https://openalex.org/W1974932989","https://openalex.org/W1995341919","https://openalex.org/W1997155350","https://openalex.org/W2008479387","https://openalex.org/W2057429658","https://openalex.org/W2064525251","https://openalex.org/W2068084671","https://openalex.org/W2100495367","https://openalex.org/W2104428789","https://openalex.org/W2109788549","https://openalex.org/W2112854909","https://openalex.org/W2133564696","https://openalex.org/W2141998673","https://openalex.org/W2402268235","https://openalex.org/W2519091744","https://openalex.org/W2553198611","https://openalex.org/W2567070169","https://openalex.org/W2666408839","https://openalex.org/W2793389773","https://openalex.org/W2896325685","https://openalex.org/W2919115771","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W3097881066","https://openalex.org/W4213100547","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6731370813","https://openalex.org/W6739901393","https://openalex.org/W6748409065"],"related_works":["https://openalex.org/W2085637247","https://openalex.org/W2424423710","https://openalex.org/W254868496","https://openalex.org/W2073905179","https://openalex.org/W2928432034","https://openalex.org/W4200277070","https://openalex.org/W1989331194","https://openalex.org/W4300740495","https://openalex.org/W1969398023","https://openalex.org/W2323643941"],"abstract_inverted_index":{"Envelope":[0],"waveforms":[1,15],"can":[2,130],"be":[3,131],"extracted":[4],"from":[5],"multiple":[6],"frequency":[7],"bands":[8],"of":[9,36,50,61,68,76,88,114],"a":[10,30,132,137],"speech":[11,22,87,140],"signal,":[12],"and":[13,45,102],"envelope":[14,38,63,143],"carry":[16],"important":[17],"intelligibility":[18,67,79],"information":[19,39,64,144],"for":[20],"human":[21,104],"communication.":[23],"This":[24],"study":[25,47],"aimed":[26],"to":[27,46,56,135],"investigate":[28],"whether":[29],"deep":[31,127],"learning-based":[32,128],"model":[33],"with":[34,141],"features":[35],"temporal":[37,62],"could":[40],"synthesize":[41,136],"an":[42],"intelligible":[43,139],"speech,":[44],"the":[48,52,66,69,85,89,103,109,125,146],"effect":[49],"reducing":[51],"number":[53],"(from":[54],"8":[55],"2":[57],"in":[58,98,145],"this":[59],"work)":[60],"on":[65,83],"synthesized":[70,86],"speech.":[71],"The":[72],"objective":[73,78],"evaluation":[74],"metric":[75],"short-time":[77],"(STOI)":[80],"showed":[81,107],"that,":[82],"average,":[84],"proposed":[90,126],"approach":[91,134],"provided":[92],"higher":[93,118],"STOI":[94],"(i.e.,":[95],"0.8)":[96],"scores":[97],"each":[99],"test":[100,106],"condition;":[101],"listening":[105],"that":[108,124],"average":[110],"word":[111],"correct":[112],"rate":[113],"eight":[115],"listeners":[116],"was":[117],"than":[119],"97.5%.":[120],"These":[121],"findings":[122],"indicated":[123],"system":[129],"potential":[133],"highly":[138],"limited":[142],"future.":[147]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
