{"id":"https://openalex.org/W4402115993","doi":"https://doi.org/10.21437/interspeech.2024-2235","title":"Sample-Efficient Diffusion for Text-To-Speech Synthesis","display_name":"Sample-Efficient Diffusion for Text-To-Speech Synthesis","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402115993","doi":"https://doi.org/10.21437/interspeech.2024-2235"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2235","doi":"https://doi.org/10.21437/interspeech.2024-2235","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2235","pdf_url":"https://www.isca-archive.org/interspeech_2024/lovelace24_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.isca-archive.org/interspeech_2024/lovelace24_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028618909","display_name":"Justin Lovelace","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Lovelace","raw_affiliation_strings":["ASAPP Inc. , USA","Cornell University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc. , USA","institution_ids":[]},{"raw_affiliation_string":"Cornell University , USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090320425","display_name":"Soham Ray","orcid":"https://orcid.org/0000-0003-1190-418X","observed_orcids":["https://orcid.org/0000-0003-1190-418X","https://orcid.org/0009-0004-8136-2536"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soham Ray","raw_affiliation_strings":["ASAPP Inc. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc. , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["ASAPP Inc. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc. , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006380227","display_name":"Kilian Q. Weinberger","orcid":"https://orcid.org/0009-0008-9313-7239","observed_orcids":["https://orcid.org/0009-0008-9313-7239"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kilian Q. Weinberger","raw_affiliation_strings":["ASAPP Inc. , USA","Cornell University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc. , USA","institution_ids":[]},{"raw_affiliation_string":"Cornell University , USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113099538","display_name":"Felix F. Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":["ASAPP Inc. , USA","Character AI , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc. , USA","institution_ids":[]},{"raw_affiliation_string":"Character AI , USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73443888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4403","last_page":"4407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/text-to-speech","display_name":"text-to-speech","score":0.9570000171661377},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.8119999766349792},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.5339999794960022},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.5899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.63150954246521},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6003780364990234},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5890899896621704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4681812822818756},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4630221724510193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33086466789245605},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08872121572494507},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-2235","doi":"https://doi.org/10.21437/interspeech.2024-2235","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2235","pdf_url":"https://www.isca-archive.org/interspeech_2024/lovelace24_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.03717","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.03717","pdf_url":"https://arxiv.org/pdf/2409.03717","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2409.03717","doi":"https://doi.org/10.48550/arxiv.2409.03717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.03717","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-2235","doi":"https://doi.org/10.21437/interspeech.2024-2235","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2235","pdf_url":"https://www.isca-archive.org/interspeech_2024/lovelace24_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402115993.pdf","grobid_xml":"https://content.openalex.org/works/W4402115993.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4285605725","https://openalex.org/W3198213150","https://openalex.org/W4392909102","https://openalex.org/W4386647763","https://openalex.org/W4375869198","https://openalex.org/W7129304879","https://openalex.org/W4285483538","https://openalex.org/W7211927311","https://openalex.org/W4399554908","https://openalex.org/W4391021721"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"Sample-Efficient":[3],"Speech":[4],"Diffusion":[5],"(SESD),":[6],"an":[7],"algorithm":[8],"for":[9],"effective":[10],"speech":[11,67,79],"synthesis":[12],"in":[13,41],"modest":[14],"data":[15],"regimes":[16],"through":[17],"latent":[18,43],"diffusion.It":[19],"is":[20,95],"based":[21],"on":[22,50,61],"a":[23,46],"novel":[24],"diffusion":[25],"architecture,":[26],"that":[27,33],"we":[28],"call":[29],"U-Audio":[30],"Transformer":[31],"(U-AT),":[32],"efficiently":[34],"scales":[35],"to":[36],"long":[37],"sequences":[38],"and":[39],"operates":[40],"the":[42,81,91],"space":[44],"of":[45,66],"pre-trained":[47],"audio":[48],"autoencoder.Conditioned":[49],"character-aware":[51],"language":[52],"model":[53],"representations,":[54],"SESD":[55],"achieves":[56],"impressive":[57],"results":[58],"despite":[59],"training":[60,92],"less":[62,69,88],"than":[63,70,80,89],"1k":[64],"hours":[65],"-far":[68],"current":[71],"state-of-the-art":[72,82],"systems.In":[73],"fact,":[74],"it":[75],"synthesizes":[76],"more":[77],"intelligible":[78],"auto-regressive":[83],"model,":[84],"VALL-E,":[85],"while":[86],"using":[87],"2%":[90],"data.Our":[93],"implementation":[94],"available":[96],"at":[97],"https://github.com/justinlovelace/SESD.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2024-09-02T00:00:00"}