{"id":"https://openalex.org/W4225943493","doi":"https://doi.org/10.1109/icassp43922.2022.9746291","title":"Distribution Augmentation for Low-Resource Expressive Text-To-Speech","display_name":"Distribution Augmentation for Low-Resource Expressive Text-To-Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225943493","doi":"https://doi.org/10.1109/icassp43922.2022.9746291"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746291","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5032468476","display_name":"Mateusz \u0141ajszczak","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mateusz Lajszczak","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016871801","display_name":"Animesh Prasad","orcid":"https://orcid.org/0000-0002-9865-6993"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Animesh Prasad","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004739281","display_name":"Arent van Korlaar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arent Van Korlaar","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064828339","display_name":"Bajibabu Bollepalli","orcid":"https://orcid.org/0000-0003-1268-0579"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bajibabu Bollepalli","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083043476","display_name":"Arnaud Joly","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnaud Joly","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054742272","display_name":"Marco Nicolis","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Nicolis","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexis Moinet","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102447937","display_name":"Trevor Wood","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Wood","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023965740","display_name":"Elena Sokolova","orcid":"https://orcid.org/0000-0002-2001-8772"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elena Sokolova","raw_affiliation_strings":["Alexa AI, Amazon,Cambridge","Alexa AI, Amazon, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Cambridge","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8307","last_page":"8311"},"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":0.9995999932289124,"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":0.9993000030517578,"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":0.8256922960281372},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7744597792625427},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7299237847328186},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6765681505203247},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6672645807266235},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4818333685398102},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4569530785083771},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43086913228034973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4241037964820862},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35665273666381836},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08248966932296753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256922960281372},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7744597792625427},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7299237847328186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6765681505203247},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6672645807266235},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4818333685398102},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4569530785083771},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43086913228034973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4241037964820862},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35665273666381836},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08248966932296753},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746291","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1526927911","https://openalex.org/W2519091744","https://openalex.org/W2775795276","https://openalex.org/W2885800352","https://openalex.org/W2889028433","https://openalex.org/W2954996726","https://openalex.org/W2963084773","https://openalex.org/W2963542120","https://openalex.org/W2964243274","https://openalex.org/W2973034126","https://openalex.org/W3003678146","https://openalex.org/W3015796413","https://openalex.org/W3022876224","https://openalex.org/W3025528898","https://openalex.org/W3035682985","https://openalex.org/W3091928890","https://openalex.org/W3114951884","https://openalex.org/W3126404598","https://openalex.org/W3161492781","https://openalex.org/W3162770051","https://openalex.org/W3173780338","https://openalex.org/W3195171908","https://openalex.org/W3198020407","https://openalex.org/W4294619240","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6631400785","https://openalex.org/W6683195492","https://openalex.org/W6747218270","https://openalex.org/W6761297928","https://openalex.org/W6778083308","https://openalex.org/W6784545093","https://openalex.org/W6787579613","https://openalex.org/W6790138166","https://openalex.org/W6797157791","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W4312531262","https://openalex.org/W4388103534","https://openalex.org/W4318142952","https://openalex.org/W2072070946"],"abstract_inverted_index":{"This":[0,37],"paper":[1],"presents":[2],"a":[3,56,92],"novel":[4],"data":[5],"augmentation":[6],"technique":[7],"for":[8],"text-to-speech":[9],"(TTS),":[10],"that":[11,58,68,85,103],"allows":[12],"to":[13,28,39,66],"generate":[14],"new":[15],"(text,":[16],"audio)":[17],"training":[18],"examples":[19],"without":[20],"requiring":[21],"any":[22],"additional":[23,64],"data.":[24],"Our":[25,46],"goal":[26],"is":[27],"in-crease":[29],"diversity":[30],"of":[31,94,108],"text":[32,51],"conditionings":[33],"available":[34],"during":[35],"training.":[36],"helps":[38],"reduce":[40],"overfitting,":[41],"especially":[42],"in":[43,55],"low-resource":[44],"settings.":[45],"method":[47,87],"relies":[48],"on":[49],"substituting":[50],"and":[52,97],"audio":[53,79],"fragments":[54],"way":[57],"preserves":[59],"syntactical":[60],"correctness.":[61],"We":[62,100],"take":[63],"measures":[65],"ensure":[67],"synthesized":[69],"speech":[70,89],"does":[71],"not":[72],"contain":[73],"artifacts":[74],"caused":[75],"by":[76],"combining":[77],"inconsistent":[78],"samples.":[80],"The":[81],"perceptual":[82],"evaluations":[83],"show":[84],"our":[86],"improves":[88,106],"quality":[90],"over":[91],"number":[93],"datasets,":[95],"speakers,":[96],"TTS":[98,110],"architectures.":[99],"also":[101],"demonstrate":[102],"it":[104],"greatly":[105],"robustness":[107],"attention-based":[109],"models.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}