{"id":"https://openalex.org/W3196866316","doi":"https://doi.org/10.21437/interspeech.2021-1011","title":"Information Sieve: Content Leakage Reduction in End-to-End Prosody Transfer for Expressive Speech Synthesis","display_name":"Information Sieve: Content Leakage Reduction in End-to-End Prosody Transfer for Expressive Speech Synthesis","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196866316","doi":"https://doi.org/10.21437/interspeech.2021-1011","mag":"3196866316"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1011","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5040845329","display_name":"Xudong Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xudong Dai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107748760","display_name":"Gong Cheng","orcid":"https://orcid.org/0009-0004-0272-3541"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050763764","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-4005-5036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100679701","display_name":"Kaili Zhang","orcid":"https://orcid.org/0000-0002-0761-1272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaili Zhang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040845329"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68754706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6968015432357788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950269937515259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.642524242401123},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45275095105171204},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.43832987546920776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42028287053108215},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41729629039764404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40051645040512085}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6968015432357788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950269937515259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.642524242401123},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45275095105171204},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.43832987546920776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42028287053108215},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41729629039764404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40051645040512085},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1011","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W2794490148","https://openalex.org/W2904459034","https://openalex.org/W2914049472","https://openalex.org/W2949281321","https://openalex.org/W2962691331","https://openalex.org/W2963394878","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2970730223","https://openalex.org/W2991417167","https://openalex.org/W3015212100","https://openalex.org/W3016021263","https://openalex.org/W3095491807","https://openalex.org/W3096738375","https://openalex.org/W3160844600"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"Expressive":[0],"neural":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4],"incorporate":[5],"a":[6,11,101,114,135],"style":[7,16,80,88,108,138],"encoder":[8,81],"to":[9,36,62,85,130],"learn":[10,134],"latent":[12,137],"embedding":[13,20],"as":[14,143,177],"the":[15,59,64,79,97,106,132,144,152,165,173,178],"information.":[17,26],"However,":[18],"this":[19,38,51,75,155],"process":[21],"may":[22],"encode":[23],"redundant":[24],"textual":[25,93],"This":[27],"phenomenon":[28],"is":[29,77],"called":[30,58],"content":[31,67,159],"leakage.":[32,160],"Researchers":[33],"have":[34],"attempted":[35],"resolve":[37],"problem":[39],"by":[40,100,120],"adding":[41],"an":[42,55],"ASR":[43],"or":[44],"other":[45],"auxiliary":[46],"supervision":[47],"loss":[48],"functions.":[49],"In":[50],"study,":[52],"we":[53,123],"propose":[54],"unsupervised":[56],"method":[57],"information":[89,94],"sieve":[61],"reduce":[63],"effect":[65],"of":[66,74,154],"leakage":[68],"in":[69,96,127,157],"prosody":[70,169],"transfer.":[71],"The":[72],"rationale":[73],"approach":[76],"that":[78,164],"can":[82,110],"be":[83,111],"forced":[84],"focus":[86],"on":[87,92],"rather":[90],"than":[91],"contained":[95],"reference":[98],"speech":[99],"well-designed":[102],"downsample-upsample":[103],"filter,":[104],"i.e.,":[105],"extracted":[107],"embeddings":[109],"downsampled":[112],"at":[113],"certain":[115],"interval":[116],"and":[117,181],"then":[118],"upsampled":[119],"duplication.":[121],"Furthermore,":[122],"used":[124],"instance":[125],"normalization":[126],"convolution":[128],"layers":[129],"help":[131],"system":[133],"better":[136],"space.":[139],"Objective":[140],"metrics":[141],"such":[142,176],"significantly":[145],"lower":[146],"word":[147],"error":[148],"rate":[149],"(WER)":[150],"demonstrate":[151],"effectiveness":[153],"model":[156,166],"mitigating":[158],"Listening":[161],"tests":[162],"indicate":[163],"retains":[167],"its":[168],"transferability":[170],"compared":[171],"with":[172],"baseline":[174],"models":[175],"original":[179],"GST-Tacotron":[180],"ASR-guided":[182],"Tacotron.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}