{"id":"https://openalex.org/W3015208154","doi":"https://doi.org/10.1109/icassp40776.2020.9054116","title":"Independent Language Modeling Architecture for End-To-End ASR","display_name":"Independent Language Modeling Architecture for End-To-End ASR","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015208154","doi":"https://doi.org/10.1109/icassp40776.2020.9054116","mag":"3015208154"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054116","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/A5046222772","display_name":"Van Tung Pham","orcid":"https://orcid.org/0000-0002-2103-1901"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Van Tung Pham","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haihua Xu","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yerbolat Khassanov","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034445480","display_name":"Zhiping Zeng","orcid":"https://orcid.org/0000-0002-6315-4408"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiping Zeng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102306089","display_name":"Chongjia Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chongjia Ni","raw_affiliation_strings":["Alibaba Group,Machine Intelligence Technology","Machine Intelligence Technology, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Machine Intelligence Technology","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group,Machine Intelligence Technology","Machine Intelligence Technology, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Machine Intelligence Technology","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.84,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88299677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7059","last_page":"7063"},"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/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":0.9983000159263611,"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/subnet","display_name":"Subnet","score":0.9523416757583618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.836558997631073},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6402642726898193},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5771015882492065},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5460441708564758},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.48530834913253784},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47348177433013916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4636157155036926},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4336596131324768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35521551966667175},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19293832778930664}],"concepts":[{"id":"https://openalex.org/C21099817","wikidata":"https://www.wikidata.org/wiki/Q7631721","display_name":"Subnet","level":2,"score":0.9523416757583618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836558997631073},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6402642726898193},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5771015882492065},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5460441708564758},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.48530834913253784},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47348177433013916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4636157155036926},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4336596131324768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35521551966667175},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19293832778930664},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/icassp40776.2020.9054116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054116","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":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1526236009","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2102113734","https://openalex.org/W2170973209","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2402302915","https://openalex.org/W2407080277","https://openalex.org/W2526425061","https://openalex.org/W2555428947","https://openalex.org/W2575842049","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2886180730","https://openalex.org/W2889028433","https://openalex.org/W2892655153","https://openalex.org/W2916997151","https://openalex.org/W2944815030","https://openalex.org/W2952468927","https://openalex.org/W2952729433","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2964012862","https://openalex.org/W2973072704","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6631545277","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6685158001","https://openalex.org/W6712909570","https://openalex.org/W6713762819","https://openalex.org/W6728030952","https://openalex.org/W6753797277","https://openalex.org/W6762521896"],"related_works":["https://openalex.org/W4319779560","https://openalex.org/W3008370744","https://openalex.org/W2019914509","https://openalex.org/W3184026069","https://openalex.org/W4290682478","https://openalex.org/W2953291251","https://openalex.org/W2786018489","https://openalex.org/W4321062926","https://openalex.org/W2608712415","https://openalex.org/W3209371554"],"abstract_inverted_index":{"The":[0],"attention-based":[1],"end-to-end":[2],"(E2E)":[3],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"architecture":[8,84,133,161],"allows":[9],"for":[10,120],"joint":[11],"optimization":[12],"of":[13,37,174],"acoustic":[14,52],"and":[15,54,141,145,153,167],"language":[16,39,56,63],"models":[17],"within":[18],"a":[19,24,82],"single":[20],"network.":[21],"However,":[22],"in":[23,77],"vanilla":[25],"E2E":[26],"ASR":[27],"architecture,":[28],"the":[29,35,38,45,51,55,87,91,97,112,122,130,159],"decoder":[30,88],"sub-network":[31],"(subnet),":[32],"which":[33,106],"incorporates":[34],"role":[36],"model":[40,57,64],"(LM),":[41],"is":[42],"conditioned":[43],"on":[44,150],"encoder":[46,53,92],"output.":[47,93],"This":[48],"means":[49],"that":[50,60,85],"are":[58],"entangled":[59],"doesn\u2019t":[61],"allow":[62],"to":[65,171],"be":[66,109,169],"trained":[67],"separately":[68],"from":[69,90,135],"external":[70,113,136,165],"text":[71,114,137],"data.":[72,115,176],"To":[73],"address":[74],"this":[75,78,95],"problem,":[76],"work,":[79],"we":[80],"propose":[81],"new":[83,123],"separates":[86],"subnet":[89,99],"In":[94],"way,":[96],"decoupled":[98],"becomes":[100],"an":[101],"independently":[102],"trainable":[103],"LM":[104,132,166],"subnet,":[105],"can":[107,168],"easily":[108],"updated":[110],"using":[111],"We":[116],"study":[117],"two":[118],"strategies":[119],"updating":[121],"architecture.":[124],"Experimental":[125],"results":[126],"show":[127],"that,":[128],"1)":[129],"independent":[131],"benefits":[134],"data,":[138],"achieving":[139],"9.3%":[140],"22.8%":[142],"relative":[143],"character":[144],"word":[146],"error":[147],"rate":[148],"reduction":[149],"Mandarin":[151],"HKUST":[152],"English":[154],"NSC":[155],"datasets":[156],"respectively;":[157],"2)":[158],"proposed":[160],"works":[162],"well":[163],"with":[164],"generalized":[170],"different":[172],"amount":[173],"labelled":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}