{"id":"https://openalex.org/W4296070422","doi":"https://doi.org/10.21437/interspeech.2022-11203","title":"When Is TTS Augmentation Through a Pivot Language Useful?","display_name":"When Is TTS Augmentation Through a Pivot Language Useful?","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070422","doi":"https://doi.org/10.21437/interspeech.2022-11203"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11203","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11203","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/A5061593862","display_name":"Nathaniel Romney Robinson","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Romney Robinson","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045030523","display_name":"Perez Ogayo","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Perez Ogayo","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065638122","display_name":"Swetha R. Gangu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swetha R. Gangu","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.8435,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74850728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3538","last_page":"3542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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":0.9955000281333923,"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":0.9939000010490417,"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":0.9811999797821045,"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":0.6697788238525391},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3853626847267151},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3620480000972748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6697788238525391},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3853626847267151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3620480000972748}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11203","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11203","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W292403927","https://openalex.org/W2574132677","https://openalex.org/W2739967986","https://openalex.org/W2889028433","https://openalex.org/W2898727538","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2964172053","https://openalex.org/W3001384475","https://openalex.org/W3006988520","https://openalex.org/W3015449694","https://openalex.org/W3015654635","https://openalex.org/W3031427604","https://openalex.org/W3096710170","https://openalex.org/W3126420472","https://openalex.org/W3162244132","https://openalex.org/W3163782004","https://openalex.org/W3198429080","https://openalex.org/W3198836239","https://openalex.org/W4210663600","https://openalex.org/W4226217936","https://openalex.org/W4296068421"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Developing":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"for":[5,72,152],"lowresource":[6],"languages":[7,46,117],"is":[8,83],"a":[9,68,73,112],"challenge":[10],"due":[11],"to":[12,102,120],"the":[13,64],"small":[14],"amount":[15],"of":[16,114,137],"transcribed":[17],"audio":[18,23,31,59],"data.For":[19],"many":[20,44],"such":[21],"languages,":[22],"and":[24,79,98,123,144,157],"text":[25,62],"are":[26],"available":[27],"separately,":[28],"but":[29],"not":[30,48],"with":[32],"transcriptions.Using":[33],"text,":[34],"speech":[35],"can":[36,118,128],"be":[37],"synthetically":[38],"produced":[39],"via":[40],"text-tospeech":[41],"(TTS)":[42],"systems.However,":[43],"low-resource":[45,87,154],"do":[47],"have":[49],"quality":[50],"TTS":[51,70,95,135],"systems":[52],"either.We":[53],"propose":[54],"an":[55],"alternative:":[56],"produce":[57],"synthetic":[58,94],"by":[60,129,131,142],"running":[61],"from":[63],"target":[65],"language":[66],"through":[67],"trained":[69],"system":[71],"higher-resource":[74],"pivot":[75,116],"language.We":[76],"investigate":[77],"when":[78],"how":[80],"this":[81],"technique":[82],"most":[84],"effective":[85],"in":[86,133],"settings.In":[88],"our":[89],"experiments,":[90],"using":[91],"several":[92],"thousand":[93],"text-speech":[96],"pairs":[97],"duplicating":[99],"authentic":[100],"data":[101],"balance":[103],"yields":[104],"optimal":[105],"results.Our":[106],"findings":[107,139],"suggest":[108],"that":[109],"searching":[110],"over":[111],"set":[113],"candidate":[115],"lead":[119],"marginal":[121],"improvements":[122],"that,":[124],"surprisingly,":[125],"ASR":[126,141],"performance":[127],"harmed":[130],"increases":[132],"measured":[134],"quality.Application":[136],"these":[138],"improves":[140],"64.5%":[143],"45.0%":[145],"character":[146],"error":[147],"reduction":[148],"rate":[149],"(CERR)":[150],"respectively":[151],"two":[153],"languages:":[155],"Guaran\u00ed":[156],"Suba.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}