{"id":"https://openalex.org/W3007901261","doi":"https://doi.org/10.1109/asru46091.2019.9003741","title":"Data Augmentation Based on Vowel Stretch for Improving Children's Speech Recognition","display_name":"Data Augmentation Based on Vowel Stretch for Improving Children's Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007901261","doi":"https://doi.org/10.1109/asru46091.2019.9003741","mag":"3007901261"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003741","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5069028016","display_name":"Tohru Nagano","orcid":"https://orcid.org/0000-0002-3686-2791"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tohru Nagano","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102876935","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0002-4601-0955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102336136","display_name":"Masayuki Suzuki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069028016"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79037383,"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":"502","last_page":"508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9987000226974487,"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":0.9699000120162964,"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/speech-recognition","display_name":"Speech recognition","score":0.804354727268219},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.7238225936889648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906809210777283},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3306514322757721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32577604055404663}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.804354727268219},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7238225936889648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906809210777283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3306514322757721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32577604055404663}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003741","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W88545716","https://openalex.org/W155159586","https://openalex.org/W434092020","https://openalex.org/W1510862247","https://openalex.org/W1984570643","https://openalex.org/W1994888226","https://openalex.org/W2039285212","https://openalex.org/W2056825827","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2094147890","https://openalex.org/W2099621636","https://openalex.org/W2117620049","https://openalex.org/W2160306971","https://openalex.org/W2187428966","https://openalex.org/W2295983515","https://openalex.org/W2396761680","https://openalex.org/W2407080277","https://openalex.org/W2407226065","https://openalex.org/W2507680812","https://openalex.org/W2511419867","https://openalex.org/W2515737026","https://openalex.org/W2516354030","https://openalex.org/W2516661016","https://openalex.org/W2548494187","https://openalex.org/W2576204408","https://openalex.org/W2696967604","https://openalex.org/W2746662897","https://openalex.org/W2750066756","https://openalex.org/W2801580204","https://openalex.org/W2916979304","https://openalex.org/W2963266252","https://openalex.org/W3034729383","https://openalex.org/W4299951565","https://openalex.org/W6606227409","https://openalex.org/W6615059388","https://openalex.org/W6675409298","https://openalex.org/W6677591559","https://openalex.org/W6712080006","https://openalex.org/W6713944695","https://openalex.org/W6732026357","https://openalex.org/W6742906757","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2121231314","https://openalex.org/W2300973977","https://openalex.org/W2025869674","https://openalex.org/W2091238608","https://openalex.org/W4386936765","https://openalex.org/W2182866171","https://openalex.org/W2052948815","https://openalex.org/W2184444734","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Prolongation":[0],"is":[1,13,22,47,51,107],"a":[2,38,63,136,150],"speech":[3,10,43,85],"disfluency":[4],"that":[5,68,112,143],"lengthens":[6],"some":[7],"portions":[8],"of":[9,41,84,93,114,155,164],"utterances.":[11],"It":[12],"frequently":[14],"observed":[15],"in":[16,24,54,119,168],"children's":[17,34,42,120],"spontaneous":[18,35,121],"speech,":[19,36],"while":[20],"it":[21],"rare":[23],"read":[25],"speech.":[26,122],"To":[27,57],"make":[28],"acoustic":[29,91,165],"models":[30],"more":[31],"robust":[32],"to":[33,87],"collecting":[37],"large":[39],"amount":[40],"data":[44,65,72],"containing":[45],"prolongation":[46],"usually":[48],"required,":[49],"which":[50,169],"very":[52],"impractical":[53],"many":[55,113],"cases.":[56],"tackle":[58],"this":[59],"problem,":[60],"we":[61],"propose":[62],"novel":[64],"augmentation":[66],"method":[67,77,142,158,172],"virtually":[69],"generates":[70],"additional":[71],"by":[73],"simulating":[74],"prolongation.":[75,89],"The":[76,90,153],"inserts":[78],"pseudo":[79],"frames":[80,96,102],"into":[81],"specific":[82],"positions":[83],"utterances":[86,130,148],"simulate":[88],"features":[92],"the":[94,100,156,162],"inserted":[95],"are":[97,116],"calculated":[98],"from":[99],"original":[101],"on":[103,109,174],"both":[104],"sides.":[105],"This":[106],"based":[108],"our":[110,170],"analysis":[111],"vowels":[115],"actually":[117],"stretched":[118,129],"Our":[123],"proposed":[124,157,171],"procedure":[125],"can":[126],"generate":[127],"partially":[128],"with":[131,161,181],"low":[132],"computational":[133],"costs,":[134],"unlike":[135],"conventional":[137,182],"speed":[138,183],"or":[139],"tempo":[140,185],"perturbation":[141,186],"extends":[144],"and":[145,184],"shrinks":[146],"entire":[147],"at":[149],"uniform":[151],"rate.":[152],"effectiveness":[154],"were":[159],"confirmed":[160],"experiments":[163],"model":[166],"adaptations,":[167],"focusing":[173],"vowel":[175],"stretch":[176],"showed":[177],"consistent":[178],"improvement":[179],"compared":[180],"approach.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}