{"id":"https://openalex.org/W4385822523","doi":"https://doi.org/10.21437/interspeech.2023-1571","title":"Adversarial Learning of Intermediate Acoustic Feature for End-to-End Lightweight Text-to-Speech","display_name":"Adversarial Learning of Intermediate Acoustic Feature for End-to-End Lightweight Text-to-Speech","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822523","doi":"https://doi.org/10.21437/interspeech.2023-1571"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1571","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5085480169","display_name":"Hyungchan Yoon","orcid":"https://orcid.org/0000-0002-6331-2437"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungchan Yoon","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074612173","display_name":"Seyun Um","orcid":"https://orcid.org/0000-0002-2229-6741"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seyun Um","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645547","display_name":"Changhwan Kim","orcid":"https://orcid.org/0000-0002-7718-4958"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changhwan Kim","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101203935","display_name":"Hong-Goo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09415704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3023","last_page":"3027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.998199999332428,"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/prosody","display_name":"Prosody","score":0.8735158443450928},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8198031783103943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646331787109375},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6848002672195435},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6392011046409607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6270782947540283},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5423939228057861},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5383616089820862},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5273502469062805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49691179394721985},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.481243371963501},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.47710472345352173},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.444691002368927},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4406391978263855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38959982991218567},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.269361287355423},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0703643262386322}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8735158443450928},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8198031783103943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646331787109375},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6848002672195435},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6392011046409607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6270782947540283},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5423939228057861},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5383616089820862},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5273502469062805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49691179394721985},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.481243371963501},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.47710472345352173},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.444691002368927},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4406391978263855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38959982991218567},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.269361287355423},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0703643262386322},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1571","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2747874407","https://openalex.org/W2787579267","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964167449","https://openalex.org/W2964243274","https://openalex.org/W2996286887","https://openalex.org/W3015338123","https://openalex.org/W3015922793","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3130774171","https://openalex.org/W3161296985","https://openalex.org/W3167533889","https://openalex.org/W3196001064","https://openalex.org/W3197273793","https://openalex.org/W4287121924","https://openalex.org/W4287761884"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"To":[0],"simplify":[1],"the":[2,44,73,86,94],"generation":[3,23],"process,":[4],"several":[5,114],"text-to-speech":[6],"(TTS)":[7],"systems":[8],"implicitly":[9],"learn":[10],"intermediate":[11],"latent":[12,45],"representations":[13,29],"instead":[14],"of":[15,89],"relying":[16],"on":[17],"predefined":[18],"features":[19,100],"(e.g.,":[20],"mel-spectrogram).However,":[21],"their":[22],"quality":[24],"is":[25],"unsatisfactory":[26],"as":[27,98],"these":[28,60],"lack":[30],"speech":[31],"variances.In":[32],"this":[33],"paper,":[34],"we":[35,48,58,70],"improve":[36],"TTS":[37],"performance":[38],"by":[39],"adding":[40],"prosody":[41,51,74,95],"embeddings":[42,52,61,75,96],"to":[43,85],"representations.During":[46],"training,":[47],"extract":[49],"reference":[50],"from":[53,62],"mel-spectrograms,":[54],"and":[55,108,121],"during":[56],"inference,":[57],"estimate":[59,72],"text":[63,107],"using":[64],"generative":[65],"adversarial":[66],"networks":[67],"(GANs).Using":[68],"GANs,":[69],"reliably":[71],"in":[76,124],"a":[77,103],"fast":[78],"way,":[79],"which":[80],"have":[81],"complex":[82],"distributions":[83],"due":[84],"dynamic":[87],"nature":[88],"speech.We":[90],"also":[91],"show":[92],"that":[93],"work":[97],"efficient":[99],"for":[101],"learning":[102],"robust":[104],"alignment":[105],"between":[106],"acoustic":[109],"features.Our":[110],"proposed":[111],"model":[112],"surpasses":[113],"publicly":[115],"available":[116],"models":[117],"with":[118],"less":[119],"parameters":[120],"computational":[122],"complexity":[123],"comparative":[125],"experiments.":[126]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2023-08-15T00:00:00"}