{"id":"https://openalex.org/W4226379831","doi":"https://doi.org/10.48550/arxiv.2204.00291","title":"Text-To-Speech Data Augmentation for Low Resource Speech Recognition","display_name":"Text-To-Speech Data Augmentation for Low Resource Speech Recognition","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W4226379831","doi":"https://doi.org/10.48550/arxiv.2204.00291"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2204.00291","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.00291","pdf_url":"https://arxiv.org/pdf/2204.00291","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.00291","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006038779","display_name":"Rodolfo Zevallos","orcid":"https://orcid.org/0000-0003-0192-7740"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zevallos, Rodolfo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006038779"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9833999872207642,"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":0.9517999887466431,"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/agglutinative-language","display_name":"Agglutinative language","score":0.8854262828826904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8050475120544434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6823879480361938},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6309652328491211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5598059296607971},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5548408031463623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5353679060935974},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5122258067131042},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4727635979652405},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4722948372364044},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.442007452249527},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17089611291885376}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.8854262828826904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050475120544434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6823879480361938},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6309652328491211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5598059296607971},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5548408031463623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353679060935974},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5122258067131042},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4727635979652405},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4722948372364044},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.442007452249527},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17089611291885376},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2204.00291","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.00291","pdf_url":"https://arxiv.org/pdf/2204.00291","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2204.00291","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.00291","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.00291","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.00291","pdf_url":"https://arxiv.org/pdf/2204.00291","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1531783358","https://openalex.org/W3217723215","https://openalex.org/W2129812225","https://openalex.org/W2029306354","https://openalex.org/W2114358883","https://openalex.org/W2050938027","https://openalex.org/W2594897229","https://openalex.org/W2134501463","https://openalex.org/W1745277","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Nowadays,":[0],"the":[1,10,19,63,66,106,115,127,131],"main":[2],"problem":[3],"of":[4,12,21,26,65,130,139],"deep":[5],"learning":[6],"techniques":[7],"used":[8],"in":[9,89,126],"development":[11],"automatic":[13],"speech":[14,94],"recognition":[15],"(ASR)":[16],"models":[17,40],"is":[18,29,70,134],"lack":[20],"transcribed":[22],"data.":[23],"The":[24,102],"goal":[25],"this":[27,77,121],"research":[28],"to":[30,37,85,91,113],"propose":[31],"a":[32,79,96,137],"new":[33,107],"data":[34,48,108],"augmentation":[35,49,109],"method":[36,50,110],"improve":[38,114],"ASR":[39,116,132],"for":[41,100,118],"agglutinative":[42,72],"and":[43,55,73,142],"low-resource":[44,74],"languages.":[45],"This":[46],"novel":[47],"generates":[51],"both":[52],"synthetic":[53,56,87,93,140,143],"text":[54,141],"audio.":[57],"Some":[58],"experiments":[59],"were":[60],"conducted":[61],"using":[62,95,136],"corpus":[64],"Quechua":[67],"language,":[68],"which":[69],"an":[71,123],"language.":[75],"In":[76,120],"study,":[78],"sequence-to-sequence":[80],"(seq2seq)":[81],"model":[82,99,117,133],"was":[83],"applied":[84],"generate":[86],"text,":[88],"addition":[90],"generating":[92],"text-to-speech":[97],"(TTS)":[98],"Quechua.":[101,119],"results":[103],"show":[104],"that":[105],"works":[111],"well":[112],"research,":[122],"8.73%":[124],"improvement":[125],"word-error-rate":[128],"(WER)":[129],"obtained":[135],"combination":[138],"speech.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}