{"id":"https://openalex.org/W4297841448","doi":"https://doi.org/10.21437/interspeech.2022-10338","title":"Low-data? No problem: low-resource, language-agnostic conversational text-to-speech via F0-conditioned data augmentation","display_name":"Low-data? No problem: low-resource, language-agnostic conversational text-to-speech via F0-conditioned data augmentation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841448","doi":"https://doi.org/10.21437/interspeech.2022-10338"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10338","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5041378836","display_name":"Giulia Comini","orcid":"https://orcid.org/0000-0002-9391-6565"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Giulia Comini","raw_affiliation_strings":["TTS Research"],"affiliations":[{"raw_affiliation_string":"TTS Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058343897","display_name":"Goeric Huybrechts","orcid":"https://orcid.org/0000-0003-0222-3008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goeric Huybrechts","raw_affiliation_strings":["TTS Research"],"affiliations":[{"raw_affiliation_string":"TTS Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["TTS Research"],"affiliations":[{"raw_affiliation_string":"TTS Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031116817","display_name":"Adam Gabry\u015b","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Gabry\u015b","raw_affiliation_strings":["TTS Research"],"affiliations":[{"raw_affiliation_string":"TTS Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["TTS Research"],"affiliations":[{"raw_affiliation_string":"TTS Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041378836"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4158,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58047835,"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":"1946","last_page":"1950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9865000247955322,"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":0.9865000247955322,"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/T12031","display_name":"Speech and dialogue systems","score":0.9672999978065491,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9064000248908997,"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/computer-science","display_name":"Computer science","score":0.7965385913848877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5994789600372314},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46072888374328613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43687188625335693},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4282686710357666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3527509570121765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965385913848877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5994789600372314},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46072888374328613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43687188625335693},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4282686710357666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3527509570121765},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10338","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2133564696","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2788357188","https://openalex.org/W2794490148","https://openalex.org/W2808706139","https://openalex.org/W2901997113","https://openalex.org/W2904459034","https://openalex.org/W2950542544","https://openalex.org/W2963691546","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2969658393","https://openalex.org/W2973034126","https://openalex.org/W2990883660","https://openalex.org/W3015586278","https://openalex.org/W3015645837","https://openalex.org/W3015805741","https://openalex.org/W3022876224","https://openalex.org/W3025680351","https://openalex.org/W3033411150","https://openalex.org/W3096303254","https://openalex.org/W3150572638","https://openalex.org/W3155308523","https://openalex.org/W3161492781","https://openalex.org/W3161890269","https://openalex.org/W3162770051","https://openalex.org/W3163573274","https://openalex.org/W3195171908","https://openalex.org/W3196584150","https://openalex.org/W3198104520","https://openalex.org/W4294619240","https://openalex.org/W4298240696","https://openalex.org/W4298857617"],"related_works":["https://openalex.org/W2216757598","https://openalex.org/W3013209356","https://openalex.org/W4387496629","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2799713421","https://openalex.org/W2951359407","https://openalex.org/W2124566234","https://openalex.org/W3192589309"],"abstract_inverted_index":{"The":[0],"availability":[1,51],"of":[2,36,52,88,122,137],"data":[3,43,55,74],"in":[4,46,56,120],"expressive":[5],"styles":[6],"across":[7,113],"languages":[8,116],"is":[9,111,118],"limited,":[10],"and":[11,16,115,117],"recording":[12],"sessions":[13],"are":[14,44],"costly":[15],"time":[17],"consuming.To":[18],"overcome":[19],"these":[20],"issues,":[21],"we":[22,59,65,78,94],"demonstrate":[23],"how":[24],"to":[25,83],"build":[26],"low-resource,":[27],"neural":[28],"text-to-speech":[29],"(TTS)":[30],"voices":[31],"with":[32],"only":[33],"1":[34],"hour":[35],"conversational":[37,42,86],"speech,":[38],"when":[39],"no":[40],"other":[41],"available":[45],"the":[47,50,85,89,101],"same":[48],"language.Assuming":[49],"non-expressive":[53],"speech":[54],"that":[57,99,105],"language,":[58],"propose":[60],"a":[61,96,125],"3-step":[62],"technology:":[63],"1)":[64],"train":[66,79,95],"an":[67,80],"F0-conditioned":[68],"voice":[69],"conversion":[70],"(VC)":[71],"model":[72],"as":[73],"augmentation":[75],"technique;":[76],"2)":[77],"F0":[81,109,138],"predictor":[82],"control":[84],"flavour":[87],"voice-converted":[90],"synthetic":[91],"data;":[92],"3)":[93],"TTS":[97],"system":[98],"consumes":[100],"augmented":[102,130],"data.We":[103],"prove":[104],"our":[106],"technology":[107],"enables":[108],"controllability,":[110],"scalable":[112],"speakers":[114],"competitive":[119],"terms":[121],"naturalness":[123],"over":[124],"state-of-the-art":[126],"baseline":[127],"model,":[128],"another":[129],"method":[131],"which":[132],"does":[133],"not":[134],"make":[135],"use":[136],"information.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}