{"id":"https://openalex.org/W4385823490","doi":"https://doi.org/10.21437/interspeech.2023-1301","title":"Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech","display_name":"Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823490","doi":"https://doi.org/10.21437/interspeech.2023-1301"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1301","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.14909","any_repository_has_fulltext":true},"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/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":"middle","author":{"id":"https://openalex.org/A5104035145","display_name":"Eunwoo Song","orcid":"https://orcid.org/0000-0003-0642-7083"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunwoo Song","raw_affiliation_strings":["NAVER Cloud, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032657615","display_name":"Hyun-Wook Yoon","orcid":"https://orcid.org/0000-0002-2849-4140"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-Wook Yoon","raw_affiliation_strings":["NAVER Cloud, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09677734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4299","last_page":"4303"},"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.9970999956130981,"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":0.7810705900192261},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6586475968360901},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6467922925949097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6431132555007935},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4863725006580353},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45925068855285645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44295862317085266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15000995993614197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810705900192261},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6586475968360901},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6467922925949097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6431132555007935},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4863725006580353},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45925068855285645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44295862317085266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15000995993614197},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1301","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"},{"id":"pmh:oai:arXiv.org:2308.14909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14909","pdf_url":"https://arxiv.org/pdf/2308.14909","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.14909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14909","pdf_url":"https://arxiv.org/pdf/2308.14909","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823490.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2153827974","https://openalex.org/W2794490148","https://openalex.org/W2808706139","https://openalex.org/W2940703732","https://openalex.org/W2964243274","https://openalex.org/W3006983028","https://openalex.org/W3024869864","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3095545636","https://openalex.org/W3128910262","https://openalex.org/W3131922516","https://openalex.org/W3161704465","https://openalex.org/W3167533889","https://openalex.org/W3168527213","https://openalex.org/W4221156079","https://openalex.org/W4221166168","https://openalex.org/W4225746985","https://openalex.org/W4287121924","https://openalex.org/W4295731579","https://openalex.org/W4309386164","https://openalex.org/W4323654151","https://openalex.org/W4360988325","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2373300491","https://openalex.org/W2371138613","https://openalex.org/W2378744544","https://openalex.org/W2048963458","https://openalex.org/W2594301978","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2379704676","https://openalex.org/W127416991"],"abstract_inverted_index":{"For":[0],"personalized":[1],"speech":[2],"generation,":[3],"a":[4,17,65,110],"neural":[5],"text-to-speech":[6],"(TTS)":[7],"model":[8,26,118],"must":[9],"be":[10,29,52],"successfully":[11],"implemented":[12],"with":[13],"limited":[14],"data":[15,34],"from":[16,85],"target":[18,36],"speaker.":[19],"To":[20,95],"this":[21,43,56],"end,":[22],"the":[23,73,93,98,117,122,130],"baseline":[24],"TTS":[25,48,74,128],"needs":[27],"to":[28,32,41,51,71,119],"amply":[30],"generalized":[31],"out-of-domain":[33,44],"(i.e.,":[35],"speaker's":[37],"speech).":[38],"However,":[39],"approaches":[40],"address":[42],"generalization":[45,76],"problem":[46],"in":[47,135],"have":[49],"yet":[50],"thoroughly":[53],"studied.":[54],"In":[55,78],"work,":[57],"we":[58,80,107],"propose":[59,109],"an":[60],"effective":[61],"pruning":[62,99,113],"method":[63,114,134],"for":[64,101],"transformer":[66],"known":[67],"as":[68],"sparse":[69],"attention,":[70],"improve":[72],"model's":[75],"abilities.":[77],"particular,":[79],"prune":[81],"off":[82],"redundant":[83],"connections":[84],"self-attention":[86],"layers":[87],"whose":[88],"attention":[89],"weights":[90],"are":[91],"below":[92],"threshold.":[94],"flexibly":[96],"determine":[97],"strength":[100],"searching":[102],"optimal":[103],"degree":[104],"of":[105,132,137],"generalization,":[106],"also":[108],"new":[111],"differentiable":[112],"that":[115],"allows":[116],"automatically":[120],"learn":[121],"thresholds.":[123],"Evaluations":[124],"on":[125],"zero-shot":[126],"multi-speaker":[127],"verify":[129],"effectiveness":[131],"our":[133],"terms":[136],"voice":[138],"quality":[139],"and":[140],"speaker":[141],"similarity.":[142]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}