{"id":"https://openalex.org/W4406461469","doi":"https://doi.org/10.1109/slt61566.2024.10832331","title":"Lite ASR Transformer: A Light Weight Transformer Architecture For Automatic Speech Recognition","display_name":"Lite ASR Transformer: A Light Weight Transformer Architecture For Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461469","doi":"https://doi.org/10.1109/slt61566.2024.10832331"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5063735369","display_name":"N J Metilda Sagaya Mary","orcid":"https://orcid.org/0000-0001-6931-4030"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"N J Metilda Sagaya Mary","raw_affiliation_strings":["Indian Institute of Technology,SPRING Lab,Madras,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,SPRING Lab,Madras,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":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Umesh","raw_affiliation_strings":["Indian Institute of Technology,SPRING Lab,Madras,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,SPRING Lab,Madras,India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063735369"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78328044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"192"},"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/T11309","display_name":"Music and Audio Processing","score":0.9932000041007996,"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/transformer","display_name":"Transformer","score":0.7791967988014221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6366845369338989},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6101354360580444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46535807847976685},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.3006667494773865},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21404123306274414},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11019295454025269}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7791967988014221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366845369338989},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6101354360580444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46535807847976685},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3006667494773865},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21404123306274414},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11019295454025269},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2134273960","https://openalex.org/W2407386500","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2972778435","https://openalex.org/W3015286511","https://openalex.org/W3033529678","https://openalex.org/W3036601975","https://openalex.org/W3049039618","https://openalex.org/W3115511229","https://openalex.org/W3144345593","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4385245566","https://openalex.org/W4386566689","https://openalex.org/W6679651198","https://openalex.org/W6753640285","https://openalex.org/W6768021236","https://openalex.org/W6774054309","https://openalex.org/W6779163297","https://openalex.org/W6780218876","https://openalex.org/W6782310929","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2864363823"],"abstract_inverted_index":{"Transformers":[0],"are":[1],"popular":[2],"sequence-to-sequence":[3],"models":[4,25,31],"but":[5],"have":[6],"large":[7],"number":[8],"of":[9,53,77,117,146],"parameters":[10,68],"and":[11,26,50,80,90,120,134,149],"high":[12],"compute":[13,49,106],"requirements.":[14],"As":[15],"an":[16],"initiative":[17],"to":[18,27,46,73,113,142],"reduce":[19,47,65,109],"the":[20,48,54,66,74,95,114,126,136,143],"energy":[21],"demand":[22],"by":[23,58,69,110],"Transformer":[24,30,40,56,67,76,99,116,130,145],"get":[28],"better":[29],"for":[32],"edge":[33],"devices,":[34],"we":[35],"propose":[36],"a":[37],"light":[38,97],"weight":[39,98],"in":[41],"this":[42],"paper.":[43],"We":[44,122],"attempt":[45],"carbon":[51],"footprint":[52],"original":[55,75,115,144],"architecture":[57],"incorporating":[59],"architectural":[60],"modifications.":[61],"The":[62,105],"proposed":[63,96,127],"modifications":[64],"42.7":[70],"%":[71],"relative":[72,112,141],"same":[78,118,147],"depth":[79,119,148],"width.":[81,121,150],"Our":[82],"automatic":[83],"speech":[84],"recognition":[85],"experiments":[86],"on":[87],"LibriSpeech,":[88],"SPGISpeech":[89],"GigaSpeech":[91],"datasets":[92],"show":[93,124],"that":[94,125],"has":[100,131],"negligible":[101],"ASR":[102,129],"performance":[103],"degradation.":[104],"requirements":[107],"also":[108,123,135],"23%":[111],"Lite":[128],"acceptable":[132],"convergence":[133],"latency":[137],"is":[138],"20%":[139],"lesser":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}