{"id":"https://openalex.org/W3016057683","doi":"https://doi.org/10.1109/icassp40776.2020.9053808","title":"Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages","display_name":"Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016057683","doi":"https://doi.org/10.1109/icassp40776.2020.9053808","mag":"3016057683"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":["Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068770030","display_name":"Metilda Sagaya Mary N. J","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":"Metilda Sagaya Mary N.J.","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, 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":3.3349,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.93774545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.7986491322517395},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6706931591033936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5100515484809875},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5011482238769531},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49192047119140625},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49135246872901917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4907428026199341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4690057933330536},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43939024209976196},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.435519814491272},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11405900120735168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986491322517395},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6706931591033936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5100515484809875},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5011482238769531},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49192047119140625},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49135246872901917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4907428026199341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690057933330536},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43939024209976196},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.435519814491272},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11405900120735168},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"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/W1524333225","https://openalex.org/W1970890968","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2327501763","https://openalex.org/W2515572005","https://openalex.org/W2766219058","https://openalex.org/W2786835190","https://openalex.org/W2808640845","https://openalex.org/W2892009249","https://openalex.org/W2894835365","https://openalex.org/W2936078256","https://openalex.org/W2941814890","https://openalex.org/W2962704885","https://openalex.org/W2962778134","https://openalex.org/W2962780374","https://openalex.org/W2963403868","https://openalex.org/W2964309797","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6739901393","https://openalex.org/W6752630080","https://openalex.org/W6761563299"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W4205302943","https://openalex.org/W2951819827","https://openalex.org/W2119949815"],"abstract_inverted_index":{"The":[0,111,130],"recent":[1],"success":[2],"of":[3,30,89],"the":[4,28,56,60,74,80,87,122,127,146],"Transformer":[5],"based":[6],"sequence-to-sequence":[7],"framework":[8],"for":[9],"various":[10,43],"Natural":[11],"Language":[12,77],"Processing":[13],"tasks":[14],"has":[15],"motivated":[16],"its":[17],"application":[18,29],"to":[19,45,73,79,121],"Automatic":[20],"Speech":[21],"Recognition.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,102],"explore":[27,42],"Transformers":[31],"on":[32],"low":[33],"resource":[34],"Indian":[35],"languages":[36],"in":[37,86,141],"a":[38,50,96],"multilingual":[39,51],"framework.":[40],"We":[41],"methods":[44,63],"incorporate":[46],"language":[47,66,71,97,106,112],"information":[48,72,78],"into":[49],"Transformer,":[52],"i.e.,":[53],"(i)":[54],"at":[55,59],"decoder,":[57],"(ii)":[58],"encoder.":[61],"These":[62],"include":[64],"using":[65],"identity":[67,107],"tokens":[68],"or":[69,93],"providing":[70,105],"acoustic":[75,81,123],"vectors.":[76],"vectors":[82],"can":[83],"be":[84],"given":[85],"form":[88],"one":[90],"hot":[91],"vector":[92],"by":[94],"learning":[95],"embedding.":[98],"From":[99],"our":[100,116],"experiments,":[101],"observed":[103],"that":[104],"always":[108],"improved":[109],"performance.":[110],"embedding":[113],"learned":[114],"from":[115],"proposed":[117,131],"approach,":[118],"when":[119],"added":[120],"feature":[124],"vector,":[125],"gave":[126,135],"best":[128],"result.":[129],"approach":[132],"with":[133],"retraining":[134],"6%":[136],"-":[137],"11%":[138],"relative":[139],"improvements":[140],"character":[142],"error":[143],"rates":[144],"over":[145],"monolingual":[147],"baseline.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}