{"id":"https://openalex.org/W3112268913","doi":"https://doi.org/10.1109/icassp39728.2021.9414169","title":"DEEPTALK: Vocal Style Encoding for Speaker Recognition and Speech Synthesis","display_name":"DEEPTALK: Vocal Style Encoding for Speaker Recognition and Speech Synthesis","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3112268913","doi":"https://doi.org/10.1109/icassp39728.2021.9414169","mag":"3112268913"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.05084","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086353379","display_name":"Anurag Chowdhury","orcid":"https://orcid.org/0000-0001-8758-988X"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Chowdhury","raw_affiliation_strings":["Michigan State University","\u2002Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"\u2002Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061834795","display_name":"Arun Ross","orcid":"https://orcid.org/0000-0001-8850-3013"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Ross","raw_affiliation_strings":["Michigan State University","\u2002Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"\u2002Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072914616","display_name":"Prabu David","orcid":"https://orcid.org/0000-0002-5096-1016"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prabu David","raw_affiliation_strings":["Michigan State University","\u2002Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"\u2002Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00909182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"6189","last_page":"6193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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/speech-recognition","display_name":"Speech recognition","score":0.8302890062332153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045452833175659},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6761021614074707},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5865323543548584},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5552611947059631},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.502068042755127},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4909959137439728},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46996423602104187},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.46838217973709106},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45210856199264526},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4336671233177185},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.42277202010154724},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41187992691993713},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38506457209587097},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.37066933512687683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35524415969848633}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8302890062332153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045452833175659},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6761021614074707},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5865323543548584},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5552611947059631},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.502068042755127},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4909959137439728},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46996423602104187},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.46838217973709106},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45210856199264526},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4336671233177185},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.42277202010154724},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41187992691993713},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38506457209587097},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.37066933512687683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35524415969848633},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.05084","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.05084","pdf_url":"https://arxiv.org/pdf/2012.05084","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3112268913","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2012.05084","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2012.05084","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.05084","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/f4gv-ce68","is_oa":true,"landing_page_url":"https://doi.org/10.17023/f4gv-ce68","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.05084","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.05084","pdf_url":"https://arxiv.org/pdf/2012.05084","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308565","display_name":"National Association of Broadcasters","ror":"https://ror.org/03pjj5012"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3112268913.pdf","grobid_xml":"https://content.openalex.org/works/W3112268913.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W165114865","https://openalex.org/W189651667","https://openalex.org/W1494198834","https://openalex.org/W1637570796","https://openalex.org/W1751091532","https://openalex.org/W1974387177","https://openalex.org/W1989674379","https://openalex.org/W2150769028","https://openalex.org/W2162273278","https://openalex.org/W2187089797","https://openalex.org/W2344822617","https://openalex.org/W2608986369","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2955515220","https://openalex.org/W2963272440","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2974062151","https://openalex.org/W3041855661","https://openalex.org/W3045051310","https://openalex.org/W3080134564","https://openalex.org/W4231627489","https://openalex.org/W6606778579","https://openalex.org/W6607727338","https://openalex.org/W6636885848","https://openalex.org/W6704529918","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6765672646","https://openalex.org/W6782256564"],"related_works":["https://openalex.org/W2171620991","https://openalex.org/W2027433780","https://openalex.org/W194278337","https://openalex.org/W2556771176","https://openalex.org/W2539843534","https://openalex.org/W2063048105","https://openalex.org/W945048957","https://openalex.org/W2112180173","https://openalex.org/W3008480565","https://openalex.org/W2163194113","https://openalex.org/W1516357917","https://openalex.org/W1533906773","https://openalex.org/W2089718722","https://openalex.org/W2143160184","https://openalex.org/W1523214805","https://openalex.org/W1560013842","https://openalex.org/W2286739582","https://openalex.org/W171560785","https://openalex.org/W3004052308","https://openalex.org/W2002276695"],"abstract_inverted_index":{"Automatic":[0],"speaker":[1,63,71,86,139],"recognition":[2,64,72,87],"algorithms":[3,23],"typically":[4],"characterize":[5],"speech":[6,20,34,84,97,109,125,134],"audio":[7,55],"using":[8],"short-term":[9],"spectral":[10],"features":[11,51],"that":[12,111],"encode":[13],"the":[14,107,112,136],"physiological":[15,83],"and":[16],"anatomical":[17],"aspects":[18],"of":[19,106,138],"production.":[21],"Such":[22],"do":[24],"not":[25],"fully":[26],"capitalize":[27],"on":[28],"speaker-dependent":[29],"characteristics":[30],"present":[31],"in":[32,135],"behavioral":[33],"features.":[35],"In":[36],"this":[37],"work,":[38],"we":[39],"propose":[40],"a":[41,81,94],"prosody":[42],"encoding":[43],"network":[44],"called":[45],"DeepTalk":[46,58,79,92,113],"for":[47,118],"extracting":[48],"vocal":[49,119],"style":[50,120],"directly":[52],"from":[53,132],"raw":[54],"data.":[56],"The":[57,70],"method":[59],"outperforms":[60],"several":[61],"state-of-the-art":[62,82,96],"systems":[65],"across":[66],"multiple":[67],"challenging":[68],"datasets.":[69],"performance":[73],"is":[74,126],"further":[75],"improved":[76],"by":[77],"combining":[78],"with":[80],"feature-based":[85],"system.":[88],"We":[89],"also":[90],"integrate":[91],"into":[93],"current":[95],"synthesizer":[98],"to":[99,128],"generate":[100],"synthetic":[101,108,124],"speech.":[102],"A":[103],"detailed":[104],"analysis":[105],"shows":[110],"captures":[114],"F0":[115],"contours":[116],"essential":[117],"modeling.":[121],"Furthermore,":[122],"DeepTalk-based":[123],"shown":[127],"be":[129],"almost":[130],"indistinguishable":[131],"real":[133],"context":[137],"recognition.":[140]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}