{"id":"https://openalex.org/W3095184753","doi":"https://doi.org/10.21437/interspeech.2020-2345","title":"Transfer Learning Approaches for Streaming End-to-End Speech Recognition System","display_name":"Transfer Learning Approaches for Streaming End-to-End Speech Recognition System","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095184753","doi":"https://doi.org/10.21437/interspeech.2020-2345","mag":"3095184753"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2345","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5019937451","display_name":"Vikas Joshi","orcid":"https://orcid.org/0000-0003-4467-3621"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vikas Joshi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065369619","display_name":"Rupesh Mehta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rupesh R. Mehta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047826067","display_name":"Kshitiz Kumar","orcid":"https://orcid.org/0000-0003-2728-2493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kshitiz Kumar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019937451"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9884,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89284606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2152","last_page":"2156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.982699990272522,"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":0.9715999960899353,"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":0.8467358350753784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7599250078201294},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5937626957893372},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4905818998813629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48184359073638916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30242088437080383},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08252525329589844}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8467358350753784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599250078201294},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5937626957893372},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4905818998813629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48184359073638916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30242088437080383},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08252525329589844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2345","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3008587939","https://openalex.org/W3127005940","https://openalex.org/W3201126466","https://openalex.org/W4387301579","https://openalex.org/W2951281592","https://openalex.org/W3123837699"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,64,82],"(TL)":[2],"is":[3,65],"widely":[4],"used":[5],"in":[6,85],"conventional":[7],"hybrid":[8,60],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"system,":[13,62],"to":[14,20,27,153],"transfer":[15,63,81],"the":[16,42,48,52,59,70,86,89,94,97,139,158],"knowledge":[17],"from":[18,55,150],"source":[19,56,77],"target":[21,49,71],"language.":[22,57],"TL":[23,114,129,142,161],"can":[24],"be":[25],"applied":[26],"end-to-end":[28],"(E2E)":[29],"ASR":[30,61],"system":[31],"such":[32],"as":[33],"recurrent":[34],"neural":[35],"network":[36,46],"transducer":[37],"(RNN-T)":[38],"models,":[39],"by":[40,68],"initializing":[41,69],"encoder":[43,101],"and/or":[44],"prediction":[45,103],"of":[47,88,96,111,141,146,160,169],"language":[50,72,78],"with":[51,76,127,143,164],"pre-trained":[53],"models":[54],"In":[58],"typically":[66],"done":[67],"acoustic":[73],"model":[74,99],"(AM)":[75],"AM.":[79],"Several":[80],"strategies":[83],"exist":[84],"case":[87],"RNN-T":[90,117,134],"framework,":[91],"depending":[92],"upon":[93],"choice":[95],"initialization":[98],"for":[100,116,162],"and":[102,156],"networks.":[104],"This":[105],"paper":[106],"presents":[107],"a":[108,165],"comparative":[109],"study":[110,138],"four":[112],"different":[113,128],"methods":[115,130],"framework.":[118],"We":[119,136],"show":[120,157],"~10%-17%":[121],"relative":[122],"word":[123],"error":[124],"rate":[125],"reduction":[126],"over":[131],"randomly":[132],"initialized":[133],"model.":[135],"also":[137],"impact":[140],"varying":[144],"amount":[145,168],"training":[147,170],"data":[148],"ranging":[149],"50":[151],"hours":[152,155],"1000":[154],"efficacy":[159],"languages":[163],"very":[166],"small":[167],"data.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}