{"id":"https://openalex.org/W3122931219","doi":"https://doi.org/10.1109/lsp.2021.3071668","title":"Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-Resource Speech Recognition","display_name":"Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-Resource Speech Recognition","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3122931219","doi":"https://doi.org/10.1109/lsp.2021.3071668","mag":"3122931219"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3071668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3071668","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.06699","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cheng Yi","orcid":"https://orcid.org/0000-0002-5851-1167"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Yi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5851-1167","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiyu Zhou","orcid":"https://orcid.org/0000-0002-6889-0316"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Zhou","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6889-0316","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bo Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.9195,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94440832,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"788","last_page":"792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.949400007724762,"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":0.949400007724762,"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":0.00800000037997961,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.003000000026077032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.633899986743927},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6241000294685364},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5877000093460083},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.46970000863075256},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.3991999924182892},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.34950000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129000067710876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7206000089645386},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.633899986743927},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6241000294685364},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5015000104904175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3991999924182892},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2021.3071668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3071668","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2101.06699","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.06699","pdf_url":"https://arxiv.org/pdf/2101.06699","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.06699","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.06699","pdf_url":"https://arxiv.org/pdf/2101.06699","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":[{"id":"https://openalex.org/G2344368435","display_name":null,"funder_award_id":"2017YFB1002102","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"}],"funders":[{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1526236009","https://openalex.org/W2127141656","https://openalex.org/W2526425061","https://openalex.org/W2750545698","https://openalex.org/W2888779557","https://openalex.org/W2889213362","https://openalex.org/W2933138175","https://openalex.org/W2936078256","https://openalex.org/W2939111082","https://openalex.org/W2953190524","https://openalex.org/W2962925243","https://openalex.org/W2963362078","https://openalex.org/W2963400424","https://openalex.org/W2963850025","https://openalex.org/W2972889948","https://openalex.org/W2973180718","https://openalex.org/W3001434439","https://openalex.org/W3016167541","https://openalex.org/W3095350795","https://openalex.org/W3097882114","https://openalex.org/W6602113894","https://openalex.org/W6675365184","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6752630080","https://openalex.org/W6755207826","https://openalex.org/W6768021236","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6775187155","https://openalex.org/W6776076330","https://openalex.org/W6777859140","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6784924749","https://openalex.org/W6787141514"],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"models":[1],"have":[2],"achieved":[3],"impressive":[4,36],"results":[5],"on":[6,87,155],"the":[7,24,40,79,94,115,131,137],"task":[8],"of":[9,26,93,136,146],"automatic":[10],"speech":[11,82],"recognition":[12,153],"(ASR).":[13],"For":[14],"low-resource":[15],"ASR":[16,37,70],"tasks,":[17],"however,":[18],"labeled":[19,89],"data":[20],"can":[21],"hardly":[22],"satisfy":[23],"demand":[25],"end-to-end":[27,49,69,162],"models.":[28,50,163],"Self-supervised":[29],"acoustic":[30,58],"pre-training":[31],"has":[32],"already":[33],"shown":[34],"its":[35],"performance,":[38],"while":[39],"transcription":[41],"is":[42,97,112],"still":[43],"inadequate":[44],"for":[45,114],"language":[46,84],"modeling":[47,134],"in":[48],"In":[51],"this":[52],"work,":[53],"we":[54],"fuse":[55],"a":[56,62,100,108,123],"pre-trained":[57,63,138,147],"encoder":[59,65],"(wav2vec2.0)":[60],"and":[61,129],"linguistic":[64,139],"(BERT)":[66],"into":[67],"an":[68],"model.":[71],"The":[72,91],"fused":[73],"model":[74,150],"only":[75],"needs":[76],"to":[77,83,127],"learn":[78],"transfer":[80],"from":[81],"during":[85],"fine-tuning":[86,125],"limited":[88],"data.":[90],"length":[92],"two":[95],"modalities":[96],"matched":[98],"by":[99],"monotonic":[101],"attention":[102],"mechanism":[103],"without":[104],"additional":[105],"parameters.":[106],"Besides,":[107],"fully":[109],"connected":[110],"layer":[111],"introduced":[113],"hidden":[116],"mapping":[117],"between":[118],"modalities.":[119],"We":[120],"further":[121],"propose":[122],"scheduled":[124],"strategy":[126],"preserve":[128],"utilize":[130],"text":[132],"context":[133],"ability":[135],"encoder.":[140],"Experiments":[141],"show":[142],"our":[143],"effective":[144],"utilizing":[145],"modules.":[148],"Our":[149],"achieves":[151],"better":[152],"performance":[154],"CALLHOME":[156],"corpus":[157],"(15":[158],"hours)":[159],"than":[160],"other":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-02-01T00:00:00"}