{"id":"https://openalex.org/W4372267440","doi":"https://doi.org/10.1109/icassp49357.2023.10096933","title":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages","display_name":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267440","doi":"https://doi.org/10.1109/icassp49357.2023.10096933"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5037738273","display_name":"Kaushal Bhogale","orcid":"https://orcid.org/0000-0002-0882-9927"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kaushal Bhogale","raw_affiliation_strings":["Indian Institute of Technology,Madras","Indian Institute of Technology, Madras","AI4Bharat"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"AI4Bharat","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035174004","display_name":"Abhigyan Raman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhigyan Raman","raw_affiliation_strings":["AI4Bharat"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI4Bharat","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044374490","display_name":"Tahir Javed","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tahir Javed","raw_affiliation_strings":["Indian Institute of Technology,Madras","Indian Institute of Technology, Madras","AI4Bharat"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"AI4Bharat","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078774993","display_name":"Sumanth Doddapaneni","orcid":"https://orcid.org/0000-0003-4248-646X"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumanth Doddapaneni","raw_affiliation_strings":["Indian Institute of Technology,Madras","AI4Bharat","Indian Institute of Technology, Madras"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"AI4Bharat","institution_ids":[]},{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052909911","display_name":"Anoop Kunchukuttan","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","IN"],"is_corresponding":false,"raw_author_name":"Anoop Kunchukuttan","raw_affiliation_strings":["Indian Institute of Technology,Madras","Indian Institute of Technology, Madras","Microsoft","AI4Bharat"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"AI4Bharat","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101614266","display_name":"Pratyush Kumar","orcid":"https://orcid.org/0000-0002-8732-0183"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pratyush Kumar","raw_affiliation_strings":["Microsoft","AI4Bharat"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"AI4Bharat","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050036814","display_name":"Mitesh M. Khapra","orcid":"https://orcid.org/0009-0008-3687-9922"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mitesh M. Khapra","raw_affiliation_strings":["Indian Institute of Technology,Madras","Indian Institute of Technology, Madras","AI4Bharat"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"AI4Bharat","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.8119404911994934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5759525299072266},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5636945962905884},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5414813160896301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4738909602165222},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4556352198123932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39586037397384644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119404911994934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5759525299072266},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5636945962905884},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5414813160896301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4738909602165222},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4556352198123932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39586037397384644},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W1488153692","https://openalex.org/W1871004397","https://openalex.org/W2052666245","https://openalex.org/W2056457557","https://openalex.org/W2074231493","https://openalex.org/W2134800885","https://openalex.org/W2330075180","https://openalex.org/W2341824394","https://openalex.org/W2747874407","https://openalex.org/W2890964092","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3099919888","https://openalex.org/W3156404059","https://openalex.org/W3160186953","https://openalex.org/W3198214208","https://openalex.org/W3211278025","https://openalex.org/W3213618310","https://openalex.org/W4382202628","https://openalex.org/W6629294717","https://openalex.org/W6679855610","https://openalex.org/W6701865325","https://openalex.org/W6704380518","https://openalex.org/W6780218876","https://openalex.org/W6842952873"],"related_works":["https://openalex.org/W2140798747","https://openalex.org/W2948169060","https://openalex.org/W2730112582","https://openalex.org/W2358580169","https://openalex.org/W2111347279","https://openalex.org/W2110696645","https://openalex.org/W2487211728","https://openalex.org/W2378096925","https://openalex.org/W2348031209","https://openalex.org/W2485376993"],"abstract_inverted_index":{"Collecting":[0],"labelled":[1,103],"datasets":[2],"for":[3,7,36,159,166],"speech":[4],"recognition":[5],"systems":[6,156],"low-resource":[8],"languages":[9,38,108,168],"on":[10],"a":[11,52,68,72,95],"diverse":[12],"set":[13],"of":[14,47,74,102,117,132,136,154],"domains":[15],"and":[16,27,33,71,88,140,162],"speakers":[17],"is":[18],"expensive.":[19],"In":[20],"this":[21],"work,":[22],"we":[23,55,145],"demonstrate":[24],"an":[25],"inexpensive":[26],"effective":[28],"alternative":[29],"by":[30],"\"mining\"":[31],"text":[32],"audio":[34,65,70,104],"pairs":[35],"Indian":[37,107],"from":[39,43],"public":[40,45],"sources,":[41],"specifically":[42],"the":[44,57,115,124,130,151],"archives":[46],"All":[48],"India":[49],"Radio.":[50],"As":[51],"key":[53],"component,":[54],"adapt":[56],"Needleman-Wunsch":[58],"algorithm":[59],"to":[60,80,84,110,150],"align":[61],"sentences":[62],"with":[63,119],"corresponding":[64],"segments":[66],"given":[67],"long":[69],"PDF":[73],"its":[75],"transcript,":[76],"while":[77],"being":[78],"robust":[79],"large":[81],"errors":[82],"due":[83],"OCR,":[85],"extraneous":[86],"text,":[87],"non-transcribed":[89],"speech.":[90],"We":[91,113,127],"thus":[92],"create":[93],"Shrutilipi,":[94],"dataset":[96,153],"which":[97],"contains":[98],"over":[99],"6,400":[100],"hours":[101],"across":[105,123,169],"12":[106,125],"totalling":[109],"3.3M":[111],"sentences.":[112],"establish":[114,129],"quality":[116],"Shrutilipi":[118,133,149],"21":[120],"human":[121],"evaluators":[122],"languages.":[126],"also":[128],"diversity":[131],"in":[134],"terms":[135],"represented":[137],"regions,":[138],"speakers,":[139],"mentioned":[141],"named":[142],"entities.":[143],"Significantly,":[144],"show":[146],"that":[147],"adding":[148],"training":[152],"ASR":[155],"improves":[157],"accuracy":[158],"both":[160],"Wav2Vec":[161],"Conformer":[163],"model":[164],"architectures":[165],"7":[167],"benchmarks.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}