{"id":"https://openalex.org/W2982696980","doi":"https://doi.org/10.1109/icassp40776.2020.9053878","title":"Lightweight and Efficient End-To-End Speech Recognition Using Low-Rank Transformer","display_name":"Lightweight and Efficient End-To-End Speech Recognition Using Low-Rank Transformer","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982696980","doi":"https://doi.org/10.1109/icassp40776.2020.9053878","mag":"2982696980"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053878","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.13923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085516032","display_name":"Genta Indra Winata","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Genta Indra Winata","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084836777","display_name":"Samuel Cahyawijaya","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Samuel Cahyawijaya","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology",", Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":", Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021691940","display_name":"Zhaojiang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhaojiang Lin","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623107","display_name":"Zihan Liu","orcid":"https://orcid.org/0000-0002-9692-4245"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zihan Liu","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE), The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Center for Artificial Intelligence Research (CAiRE)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085516032"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":1.9199,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88538354,"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":"6144","last_page":"6148"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech 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/end-to-end-principle","display_name":"End-to-end principle","score":0.7783710956573486},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7615358829498291},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7548172473907471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7254831790924072},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5857549905776978},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5308125019073486},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5042797327041626},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4128718078136444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4032588303089142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3587448000907898},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11612668633460999}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7783710956573486},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7615358829498291},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7548172473907471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254831790924072},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5857549905776978},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5308125019073486},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5042797327041626},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4128718078136444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4032588303089142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587448000907898},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11612668633460999},{"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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053878","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"},{"id":"pmh:oai:arXiv.org:1910.13923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13923","pdf_url":"https://arxiv.org/pdf/1910.13923","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2982696980","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.13923.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-102034","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85089240410&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-102034","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-102034","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.1910.13923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.13923","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/dx20-1830","is_oa":true,"landing_page_url":"https://doi.org/10.17023/dx20-1830","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.13923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13923","pdf_url":"https://arxiv.org/pdf/1910.13923","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982696980.pdf","grobid_xml":"https://content.openalex.org/works/W2982696980.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1526236009","https://openalex.org/W2058641082","https://openalex.org/W2102113734","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2526425061","https://openalex.org/W2627092829","https://openalex.org/W2892009249","https://openalex.org/W2936078256","https://openalex.org/W2949975180","https://openalex.org/W2962835968","https://openalex.org/W2963070863","https://openalex.org/W2963242190","https://openalex.org/W2963385194","https://openalex.org/W2963403868","https://openalex.org/W2970418186","https://openalex.org/W2972470300","https://openalex.org/W2972736078","https://openalex.org/W2989143494","https://openalex.org/W6637373629","https://openalex.org/W6675365184","https://openalex.org/W6736198902","https://openalex.org/W6739901393","https://openalex.org/W6767215405"],"related_works":["https://openalex.org/W3195113351","https://openalex.org/W2901459357","https://openalex.org/W2962956675","https://openalex.org/W2902991518","https://openalex.org/W2891335318","https://openalex.org/W2612264667","https://openalex.org/W2892799969","https://openalex.org/W2788153607","https://openalex.org/W2890770683","https://openalex.org/W2777406049","https://openalex.org/W2981494268","https://openalex.org/W2911892981","https://openalex.org/W3185946996","https://openalex.org/W3181793056","https://openalex.org/W3104882907","https://openalex.org/W3188045955","https://openalex.org/W3115734461","https://openalex.org/W2950779027","https://openalex.org/W2962761403","https://openalex.org/W3199118778"],"abstract_inverted_index":{"Highly":[0],"performing":[1],"deep":[2],"neural":[3,31],"networks":[4],"come":[5],"at":[6],"the":[7,23,36,40,53,58,67,75],"cost":[8],"of":[9,42,55,57],"computational":[10],"complexity":[11],"that":[12,33,82],"limits":[13],"their":[14],"practicality":[15],"for":[16,46],"deployment":[17],"on":[18,93,113],"portable":[19],"devices.":[20],"We":[21],"propose":[22],"low-rank":[24],"transformer":[25,77,103],"(LRT),":[26],"a":[27],"memory-efficient":[28],"and":[29,38,44,64,88,96],"fast":[30],"architecture":[32],"significantly":[34],"reduces":[35,52],"parameters":[37,56],"boosts":[39],"speed":[41],"training":[43],"inference":[45,68],"end-to-end":[47,118],"speech":[48],"recognition.":[49],"Our":[50],"approach":[51],"number":[54],"network":[59],"by":[60,70],"more":[61],"than":[62],"50%":[63],"speeds":[65],"up":[66],"time":[69],"around":[71],"1.35x":[72],"compared":[73,99],"to":[74,100],"baseline":[76],"model.":[78,104],"The":[79,105],"experiments":[80],"show":[81],"our":[83],"LRT":[84,106],"model":[85,107,125],"generalizes":[86],"better":[87],"yields":[89],"lower":[90],"error":[91],"rates":[92],"both":[94],"validation":[95],"test":[97],"sets":[98],"an":[101,117,122],"uncompressed":[102],"outperforms":[108],"those":[109],"from":[110],"existing":[111],"works":[112],"several":[114],"datasets":[115],"in":[116],"setting":[119],"without":[120],"using":[121],"external":[123],"language":[124],"or":[126],"acoustic":[127],"data.":[128]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}