{"id":"https://openalex.org/W2972471621","doi":"https://doi.org/10.1109/access.2019.2940700","title":"Whisper to Normal Speech Conversion Using Sequence-to-Sequence Mapping Model With Auditory Attention","display_name":"Whisper to Normal Speech Conversion Using Sequence-to-Sequence Mapping Model With Auditory Attention","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972471621","doi":"https://doi.org/10.1109/access.2019.2940700","mag":"2972471621"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2940700","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940700","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835014.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835014.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103280008","display_name":"Hailun Lian","orcid":"https://orcid.org/0000-0002-0519-8568"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailun Lian","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102016818","display_name":"Yuting Hu","orcid":"https://orcid.org/0000-0002-5677-9952"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Hu","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111203940","display_name":"Wei-Wei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Yu","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067137933","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0001-6509-5520"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6509-5520","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029771864","display_name":"Wenming Zheng","orcid":"https://orcid.org/0000-0002-7764-5179"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Zheng","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7764-5179","affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.3352,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.81690912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"130495","last_page":"130504"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9905999898910522,"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/computer-science","display_name":"Computer science","score":0.7621959447860718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7531617879867554},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6101608872413635},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.554300844669342},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.535686731338501},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5352374315261841},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4783020615577698},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4676266312599182},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41913264989852905},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3229326903820038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30184054374694824},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20687764883041382},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1282859444618225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621959447860718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7531617879867554},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6101608872413635},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.554300844669342},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.535686731338501},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5352374315261841},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4783020615577698},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4676266312599182},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41913264989852905},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3229326903820038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30184054374694824},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20687764883041382},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1282859444618225},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2940700","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940700","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835014.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4712a90c9f1443f589fb1710e6ad562d","is_oa":true,"landing_page_url":"https://doaj.org/article/4712a90c9f1443f589fb1710e6ad562d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 130495-130504 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2940700","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940700","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835014.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G528582976","display_name":null,"funder_award_id":"61301295","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6861789708","display_name":null,"funder_award_id":"1708085MF151","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972471621.pdf","grobid_xml":"https://content.openalex.org/works/W2972471621.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W162035042","https://openalex.org/W1187407439","https://openalex.org/W1540787848","https://openalex.org/W2047233879","https://openalex.org/W2049686551","https://openalex.org/W2056852181","https://openalex.org/W2066502876","https://openalex.org/W2067295501","https://openalex.org/W2071431631","https://openalex.org/W2106790438","https://openalex.org/W2107860279","https://openalex.org/W2116261113","https://openalex.org/W2119648481","https://openalex.org/W2120605154","https://openalex.org/W2131774270","https://openalex.org/W2154920538","https://openalex.org/W2157331557","https://openalex.org/W2162223813","https://openalex.org/W2363995577","https://openalex.org/W2400434184","https://openalex.org/W2416718102","https://openalex.org/W2437658533","https://openalex.org/W2477452846","https://openalex.org/W2607377433","https://openalex.org/W2768731046","https://openalex.org/W2775672830","https://openalex.org/W2889417860","https://openalex.org/W6606511802","https://openalex.org/W6632127171","https://openalex.org/W6712874156"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2081919107","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W1540615732","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W3115948027","https://openalex.org/W4200562864","https://openalex.org/W2405110677"],"abstract_inverted_index":{"Whispering":[0],"is":[1,19,34,49,104,130],"a":[2,26,64,71],"special":[3],"pronunciation":[4],"style":[5],"in":[6],"which":[7,91,129],"the":[8,23,101,107,114,123,134,140,148],"vocal":[9],"cords":[10],"do":[11],"not":[12,84],"vibrate.":[13],"Compared":[14],"with":[15,75],"voiced":[16,42,119],"speech,":[17],"whispering":[18,45],"noise-like":[20],"because":[21],"of":[22,25,31,41],"lack":[24],"fundamental":[27,102],"frequency.":[28],"The":[29,80,118],"energy":[30],"whispered":[32,142],"speech":[33,48,55,66,120,152],"approximately":[35],"20":[36],"dB":[37],"lower":[38],"than":[39],"that":[40,147],"speech.":[43,143],"Converting":[44],"into":[46],"normal":[47],"an":[50,76],"effective":[51],"way":[52],"to":[53,96,139],"improve":[54],"quality":[56],"and/or":[57],"intelligibility.":[58],"In":[59,99],"this":[60],"paper,":[61],"we":[62],"propose":[63],"whisper-to-normal":[65,151],"conversion":[67,89,153],"method":[68,82,125,154],"based":[69],"on":[70],"sequence-to-sequence":[72,116,136,150],"framework":[73],"combined":[74],"auditory":[77],"attention":[78],"mechanism.":[79],"proposed":[81,115,124,135,149],"does":[83],"require":[85],"time":[86],"aligning":[87],"before":[88],"training,":[90],"makes":[92],"it":[93],"more":[94],"applicable":[95],"real":[97],"scenarios.":[98],"addition,":[100],"frequency":[103,109],"estimated":[105,112],"from":[106],"mel":[108],"cepstral":[110],"coefficients":[111],"by":[113,122,133],"framework.":[117],"converted":[121],"has":[126],"appropriate":[127],"length,":[128],"determined":[131],"adaptively":[132],"model":[137],"according":[138],"source":[141],"Experimental":[144],"results":[145],"show":[146],"outperforms":[155],"conventional":[156],"DTW-based":[157],"methods.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}