{"id":"https://openalex.org/W4283837596","doi":"https://doi.org/10.21437/interspeech.2022-233","title":"Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)","display_name":"Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283837596","doi":"https://doi.org/10.21437/interspeech.2022-233"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-233","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-233","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":"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/A5107424977","display_name":"Ariadna S\u00e1nchez","orcid":"https://orcid.org/0000-0003-0409-1328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ariadna Sanchez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010492282","display_name":"Alessio Falai","orcid":"https://orcid.org/0000-0002-6574-5607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessio Falai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004044","display_name":"Ziyao Zhang","orcid":"https://orcid.org/0000-0002-0617-1340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083300352","display_name":"Orazio Angelini","orcid":"https://orcid.org/0000-0002-5057-7866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Orazio Angelini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2963","last_page":"2967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/polyglot","display_name":"Polyglot","score":0.9655306339263916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7943398952484131},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6112575531005859},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5745871067047119},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5672388672828674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557375550270081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48725906014442444},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.4255129098892212},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42539262771606445},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2539970874786377},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06552621722221375}],"concepts":[{"id":"https://openalex.org/C2780239667","wikidata":"https://www.wikidata.org/wiki/Q2102850","display_name":"Polyglot","level":2,"score":0.9655306339263916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943398952484131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6112575531005859},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5745871067047119},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5672388672828674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557375550270081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48725906014442444},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.4255129098892212},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42539262771606445},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2539970874786377},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06552621722221375},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-233","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-233","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","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W2016589492","https://openalex.org/W2130942839","https://openalex.org/W2181963777","https://openalex.org/W2316803017","https://openalex.org/W2794235490","https://openalex.org/W2963542120","https://openalex.org/W2963609956","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2973213036","https://openalex.org/W3016090709","https://openalex.org/W3048217770","https://openalex.org/W3162770051","https://openalex.org/W3195171908","https://openalex.org/W3195366621","https://openalex.org/W3197287223","https://openalex.org/W3198032048","https://openalex.org/W3207068396","https://openalex.org/W4225680573","https://openalex.org/W4283824751","https://openalex.org/W4287599683","https://openalex.org/W4287776643","https://openalex.org/W4294410884","https://openalex.org/W4295731579"],"related_works":["https://openalex.org/W3021456553","https://openalex.org/W4287790127","https://openalex.org/W3034786336","https://openalex.org/W4243497717","https://openalex.org/W2788843600","https://openalex.org/W2808486486","https://openalex.org/W2807814100","https://openalex.org/W2486417041","https://openalex.org/W2772686614","https://openalex.org/W2482180524"],"abstract_inverted_index":{"An":[0],"essential":[1],"design":[2],"decision":[3],"for":[4,54],"multilingual":[5,65,162],"Neural":[6],"Text-To-Speech":[7],"(NTTS)":[8],"systems":[9,67],"is":[10],"how":[11],"to":[12,86,93,117],"represent":[13],"input":[14],"linguistic":[15],"features":[16],"within":[17],"the":[18,21,27,48,76,119,122,126,129,134,137,157],"model.Looking":[19],"at":[20],"wide":[22],"variety":[23],"of":[24,42,97,121,128],"approaches":[25],"in":[26],"literature,":[28],"two":[29,138],"main":[30],"paradigms":[31,139],"emerge,":[32],"unified":[33,77,102,153],"and":[34,89],"separate":[35],"representations.The":[36],"former":[37],"uses":[38,50],"a":[39,61,143],"shared":[40],"set":[41],"phonetic":[43,52],"tokens":[44,53,100],"across":[45],"languages,":[46],"whereas":[47],"latter":[49],"unique":[51],"each":[55],"language.In":[56],"this":[57,109],"paper,":[58],"we":[59,111],"conduct":[60],"comprehensive":[62],"study":[63,116,148],"comparing":[64],"NTTS":[66,163],"models":[68],"trained":[69],"with":[70,84,125],"both":[71,87],"representations.Our":[72],"results":[73],"reveal":[74],"that":[75,133,152],"approach":[78],"consistently":[79],"achieves":[80],"better":[81],"crosslingual":[82],"synthesis":[83],"respect":[85],"naturalness":[88],"accent.Separate":[90],"representations":[91,154],"tend":[92],"have":[94],"an":[95,114],"order":[96],"magnitude":[98],"more":[99],"than":[101],"ones,":[103],"which":[104],"may":[105],"affect":[106],"model":[107],"capacity.For":[108],"reason,":[110],"carry":[112],"out":[113],"ablation":[115],"understand":[118],"interaction":[120],"representation":[123],"type":[124],"size":[127],"token":[130],"embedding.We":[131],"find":[132],"difference":[135],"between":[136],"only":[140],"emerges":[141],"above":[142],"certain":[144],"threshold":[145],"embedding":[146],"size.This":[147],"provides":[149],"strong":[150],"evidence":[151],"should":[155],"be":[156],"preferred":[158],"paradigm":[159],"when":[160],"building":[161],"systems.":[164]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}