{"id":"https://openalex.org/W3160186953","doi":"https://doi.org/10.1109/icassp39728.2021.9414961","title":"Exploring the use of Common Label Set to Improve Speech Recognition of Low Resource Indian Languages","display_name":"Exploring the use of Common Label Set to Improve Speech Recognition of Low Resource Indian Languages","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160186953","doi":"https://doi.org/10.1109/icassp39728.2021.9414961","mag":"3160186953"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5043963608","display_name":"Vishwas M. Shetty","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":"Vishwas M. Shetty","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"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":"S. Umesh","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":1.6118,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86281091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7228","last_page":"7232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/cls-upper-limits","display_name":"CLs upper limits","score":0.8642700910568237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818259596824646},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6557897329330444},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6339508295059204},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.61811363697052},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5586411356925964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5292555689811707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48674845695495605},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4788215756416321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46830856800079346},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1393936276435852},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07289442420005798}],"concepts":[{"id":"https://openalex.org/C190729725","wikidata":"https://www.wikidata.org/wiki/Q5012817","display_name":"CLs upper limits","level":2,"score":0.8642700910568237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818259596824646},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6557897329330444},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6339508295059204},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.61811363697052},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5586411356925964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5292555689811707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48674845695495605},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4788215756416321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46830856800079346},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1393936276435852},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07289442420005798},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C119767625","wikidata":"https://www.wikidata.org/wiki/Q618211","display_name":"Optometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1524333225","https://openalex.org/W2510374792","https://openalex.org/W2766219058","https://openalex.org/W2808640845","https://openalex.org/W2809978471","https://openalex.org/W2892009249","https://openalex.org/W2914120296","https://openalex.org/W2936078256","https://openalex.org/W2941814890","https://openalex.org/W2962778134","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963403868","https://openalex.org/W2970049541","https://openalex.org/W2972818416","https://openalex.org/W2973213036","https://openalex.org/W3007328579","https://openalex.org/W3015445672","https://openalex.org/W3015887631","https://openalex.org/W3016057683","https://openalex.org/W4385245566","https://openalex.org/W6601894380","https://openalex.org/W6631362777","https://openalex.org/W6739901393","https://openalex.org/W6752630080","https://openalex.org/W6761563299","https://openalex.org/W6767737316"],"related_works":["https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3161911362","https://openalex.org/W2945824677","https://openalex.org/W3035522059","https://openalex.org/W2892009249","https://openalex.org/W2547835662","https://openalex.org/W142374489","https://openalex.org/W3196747313","https://openalex.org/W3104417388"],"abstract_inverted_index":{"In":[0],"many":[1,21,100],"Indian":[2,101],"languages,":[3],"written":[4],"characters":[5,16,36,53,95],"are":[6,105],"organized":[7],"on":[8,132,171],"sound":[9],"phonetic":[10],"principles,":[11],"and":[12,159],"the":[13,18,48,61,92,97,115,120,133,138,144,175,180],"ordering":[14,93],"of":[15,22,51,63,94,125,174,182,186],"is":[17,54,96,189],"same":[19,98],"across":[20],"them.":[23],"However,":[24],"while":[25],"training":[26],"conventional":[27],"end-to-end":[28],"(E2E)":[29],"Multilingual":[30],"speech":[31],"recognition":[32],"systems,":[33],"we":[34,59,135],"treat":[35],"or":[37],"target":[38,67],"subword":[39,68],"units":[40,69,127,141],"from":[41],"different":[42],"languages":[43],"as":[44,118],"separate":[45,164],"entities.":[46],"Since":[47],"visual":[49],"rendering":[50],"these":[52],"different,":[55],"in":[56,99,128],"this":[57,187],"paper,":[58],"explore":[60],"benefits":[62,181],"representing":[64],"such":[65],"similar":[66],"(e.g.,":[70],"Byte":[71],"Pair":[72],"Encoded(BPE)":[73],"units)":[74],"through":[75],"a":[76,108,123,160,172],"Common":[77],"Label":[78],"Set":[79],"(CLS).":[80],"The":[81],"CLS":[82,129,140,154,197],"can":[83],"be":[84],"very":[85],"easily":[86],"created":[87],"using":[88,107,153,196],"automatic":[89],"methods":[90],"since":[91],"Languages.":[102],"E2E":[103],"models":[104,151],"trained":[106,152,198],"transformer-based":[109],"encoder-decoder":[110],"architecture.":[111],"During":[112],"testing,":[113],"given":[114],"Mel-filterbank":[116],"features":[117],"input,":[119],"system":[121],"outputs":[122],"sequence":[124],"BPE":[126],"representation.":[130,147],"Depending":[131],"language,":[134],"then":[136],"map":[137],"recognized":[139],"back":[142],"to":[143,190],"language-specific":[145],"grapheme":[146],"Results":[148],"show":[149],"that":[150],"improve":[155],"over":[156],"monolingual":[157],"baseline":[158],"multilingual":[161],"framework":[162],"with":[163],"symbols":[165],"for":[166],"each":[167],"language.":[168],"Similar":[169],"experiments":[170],"subset":[173],"Voxforge":[176],"dataset":[177],"also":[178],"confirm":[179],"CLS.":[183],"An":[184],"extension":[185],"idea":[188],"decode":[191],"an":[192],"unseen":[193],"language":[194],"(Zero-resource)":[195],"model.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}