{"id":"https://openalex.org/W4210723584","doi":"https://doi.org/10.1109/asru51503.2021.9688074","title":"On-The-Fly Data Augmentation for Text-to-Speech Style Transfer","display_name":"On-The-Fly Data Augmentation for Text-to-Speech Style Transfer","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210723584","doi":"https://doi.org/10.1109/asru51503.2021.9688074"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688074","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5020069661","display_name":"Raymond T. Chung","orcid":"https://orcid.org/0000-0001-7587-718X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210131801","display_name":"Hong Kong R&D Centre for Logistics and Supply Chain Management Enabling Technologies","ror":"https://ror.org/03nm59d75","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210131801"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Raymond Chung","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Computer Science and Engineering","Logistics and Supply Chain MultiTech R&D Centre, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Logistics and Supply Chain MultiTech R&D Centre, Hong Kong","institution_ids":["https://openalex.org/I4210131801"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020069661"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4210131801"],"apc_list":null,"apc_paid":null,"fwci":0.5026,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67919237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"25","issue":null,"first_page":"634","last_page":"641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.987500011920929,"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":0.7119845151901245},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6403595805168152},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5316807627677917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4824443459510803},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4209473133087158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39475929737091064},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.060150742530822754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7119845151901245},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6403595805168152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5316807627677917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4824443459510803},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4209473133087158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39475929737091064},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.060150742530822754},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru51503.2021.9688074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688074","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-114668","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85126732383&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"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":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2163605009","https://openalex.org/W2519091744","https://openalex.org/W2747874407","https://openalex.org/W2794490148","https://openalex.org/W2885800352","https://openalex.org/W2914049472","https://openalex.org/W2938833595","https://openalex.org/W2940703732","https://openalex.org/W2941649920","https://openalex.org/W2942807473","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2973164261","https://openalex.org/W3015645837","https://openalex.org/W3022876224","https://openalex.org/W3094650042","https://openalex.org/W3094785744","https://openalex.org/W3097587372","https://openalex.org/W3146104336","https://openalex.org/W3161492781","https://openalex.org/W6631190155","https://openalex.org/W6743149223","https://openalex.org/W6750489868","https://openalex.org/W6768830310"],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W4313326281","https://openalex.org/W574867512","https://openalex.org/W2387271333","https://openalex.org/W581389233","https://openalex.org/W2361120309","https://openalex.org/W632157940","https://openalex.org/W2387981414","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"advanced":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4],"synthesize":[5,16],"natural":[6],"speeches.":[7],"However,":[8],"in":[9,18,77,172],"many":[10],"applications,":[11],"it":[12],"is":[13],"desirable":[14],"to":[15,87,112,127],"utterances":[17],"a":[19,40,89,125,194],"specific":[20],"style.":[21,81],"In":[22],"this":[23],"paper,":[24],"we":[25],"investigate":[26],"synthesizing":[27],"audios":[28,97],"with":[29,101,163],"three":[30,133],"styles":[31,66,171],"\u2014":[32,38],"news-casting,":[33],"public":[34],"speaking":[35],"and":[36,58,109,150],"storytelling":[37],"for":[39],"speaker":[41,126],"who":[42],"provides":[43],"only":[44],"neutral":[45,56],"speech":[46,50,62,156,170],"data.":[47],"Firstly,":[48],"considerable":[49],"data":[51,84,120,166],"were":[52,67,85,98,110,121],"collected":[53,68],"from":[54,63,69,193],"the":[55,64,83,102,115,148,154,159],"speaker,":[57],"small":[59],"amounts":[60],"of":[61,131,153],"wanted":[65],"other":[70,132],"speakers":[71,75,134],"such":[72],"that":[73,158,180],"no":[74],"uttered":[76],"more":[78],"than":[79,191],"one":[80],"All":[82],"used":[86,111],"train":[88,114],"basic":[90],"multi-style":[91],"multi-speaker":[92],"TTS":[93,104,116,160,196],"model.":[94,117],"Secondly,":[95],"augmented":[96,119],"created":[99,122],"on-the-fly":[100],"latest":[103],"model":[105,161,197],"during":[106],"its":[107],"training":[108],"further":[113],"Specifically,":[118],"by":[123,135,184,198],"\u2018forcing\u2019":[124],"imitate":[128],"stylish":[129,181],"speeches":[130,182],"requiring":[136],"their":[137],"attention":[138],"alignment":[139],"matrices":[140],"as":[141,143],"similar":[142],"possible.":[144],"Objective":[145],"evaluation":[146,177],"on":[147],"rhythm":[149],"pitch":[151],"profile":[152],"synthesized":[155,183],"shows":[157,179],"trained":[162],"our":[164,185],"proposed":[165,186],"augmentation":[167],"successfully":[168],"transfers":[169],"these":[173],"aspects.":[174],"Subjective":[175],"ABX":[176],"also":[178],"method":[187],"are":[188],"overwhelmingly":[189],"preferred":[190],"those":[192],"baseline":[195],"40-60%.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}