{"id":"https://openalex.org/W2889385306","doi":"https://doi.org/10.21437/interspeech.2018-1555","title":"Effect of TTS Generated Audio on OOV Detection and Word Error Rate in ASR for Low-resource Languages","display_name":"Effect of TTS Generated Audio on OOV Detection and Word Error Rate in ASR for Low-resource Languages","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889385306","doi":"https://doi.org/10.21437/interspeech.2018-1555","mag":"2889385306"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1555","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5084244030","display_name":"Savitha Murthy","orcid":"https://orcid.org/0000-0001-7560-0420"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Savitha Murthy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008942513","display_name":"Dinkar Sitaram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinkar Sitaram","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005513786","display_name":"Sunayana Sitaram","orcid":"https://orcid.org/0000-0003-4251-9719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunayana Sitaram","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084244030"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79703346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1026","last_page":"1030"},"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9954000115394592,"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/speech-recognition","display_name":"Speech recognition","score":0.7993525266647339},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7979085445404053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7753336429595947},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7470191717147827},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5590721368789673},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5579403042793274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46994808316230774},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4365732669830322},{"id":"https://openalex.org/keywords/kannada","display_name":"Kannada","score":0.4271516799926758},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4236147403717041},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09571856260299683},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07238563895225525}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7993525266647339},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7979085445404053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753336429595947},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7470191717147827},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5590721368789673},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5579403042793274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46994808316230774},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4365732669830322},{"id":"https://openalex.org/C2778579358","wikidata":"https://www.wikidata.org/wiki/Q33673","display_name":"Kannada","level":2,"score":0.4271516799926758},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4236147403717041},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09571856260299683},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07238563895225525},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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.2018-1555","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W58893626","https://openalex.org/W139927782","https://openalex.org/W626798658","https://openalex.org/W647527196","https://openalex.org/W1501139663","https://openalex.org/W1865731626","https://openalex.org/W1987899306","https://openalex.org/W1992673181","https://openalex.org/W1993994668","https://openalex.org/W2000654171","https://openalex.org/W2039488303","https://openalex.org/W2073936927","https://openalex.org/W2101059451","https://openalex.org/W2111377197","https://openalex.org/W2166850712","https://openalex.org/W2407420912","https://openalex.org/W2507202298","https://openalex.org/W2508297107","https://openalex.org/W2510438986","https://openalex.org/W2510707763","https://openalex.org/W2511001748","https://openalex.org/W2513564957","https://openalex.org/W2578686723","https://openalex.org/W2592226044","https://openalex.org/W4299951565"],"related_works":["https://openalex.org/W2099074650","https://openalex.org/W2132658536","https://openalex.org/W2061937230","https://openalex.org/W1937192591","https://openalex.org/W2130106985","https://openalex.org/W1931781377","https://openalex.org/W2134501463","https://openalex.org/W2122544684","https://openalex.org/W1860937202","https://openalex.org/W2356301199"],"abstract_inverted_index":{"Out-of-Vocabulary":[0],"(OOV)":[1],"detection":[2,29,83,133],"and":[3,30,47,65,84],"recovery":[4,31,85],"is":[5],"an":[6,114,129],"important":[7],"aspect":[8],"of":[9,27,44,107,137],"reducing":[10],"Word":[11],"Error":[12],"Rate":[13],"(WER)":[14],"in":[15,91,131],"Automatic":[16],"Speech":[17],"Recognition":[18],"(ASR).":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"evaluate":[24],"the":[25,49,53,67,79,92],"effect":[26,80],"OOV":[28,55,63,82,132],"for":[32,119],"a":[33,40,59,96,142],"low-resource":[34],"language":[35],"on":[36,81],"WER.":[37],"We":[38,57,112],"use":[39,58,113],"small":[41],"seed":[42],"corpus":[43],"continuous":[45,108],"speech":[46,109],"improve":[48],"vocabulary":[50],"by":[51],"incorporating":[52],"detected":[54],"words.":[56],"syllable-model":[60],"to":[61,73,121,135],"learn":[62],"words":[64,71],"augment":[66],"word-model":[68],"with":[69],"these":[70],"leading":[72],"improved":[74],"recognition.":[75],"Our":[76,100,125],"research":[77],"investigates":[78],"after":[86],"adding":[87],"missing":[88,138],"syllable":[89,93,139],"sounds":[90,140],"model":[94],"using":[95,104,141],"Text-to-Speech":[97],"(TTS)":[98],"system.":[99,145],"experiments":[101,127],"are":[102],"conducted":[103],"5":[105],"hours":[106],"Kannada":[110,123],"corpus.":[111],"already":[115],"available":[116],"Festival":[117],"TTS":[118,144],"Hindi":[120],"generate":[122],"speech.":[124],"initial":[126],"report":[128],"improvement":[130],"due":[134],"addition":[136],"cross-lingual":[143]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}