{"id":"https://openalex.org/W3094780479","doi":"https://doi.org/10.21437/interspeech.2020-2141","title":"Combination of End-to-End and Hybrid Models for Speech Recognition","display_name":"Combination of End-to-End and Hybrid Models for Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3094780479","doi":"https://doi.org/10.21437/interspeech.2020-2141","mag":"3094780479"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2141","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2141","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":"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/A5048201022","display_name":"Jeremy H. M. Wong","orcid":"https://orcid.org/0000-0003-3742-7510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeremy H.M. Wong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090360853","display_name":"Eric Sun","orcid":"https://orcid.org/0000-0001-8805-9864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1783","last_page":"1787"},"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":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8298234343528748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6362855434417725},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.632502555847168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2644299864768982}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8298234343528748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6362855434417725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.632502555847168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2644299864768982}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2141","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2141","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W126222424","https://openalex.org/W1828163288","https://openalex.org/W1904457459","https://openalex.org/W1991133427","https://openalex.org/W1993721840","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2515439472","https://openalex.org/W2526425061","https://openalex.org/W2594610113","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2962907457","https://openalex.org/W3011339933"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Recent":[0],"studies":[1,59],"suggest":[2],"that":[3,16,132],"it":[4],"may":[5,37,52,88],"now":[6],"be":[7,103,136],"possible":[8],"to":[9,105],"construct":[10],"end-to-end":[11,69,73,145],"Neural":[12],"Network":[13],"(NN)":[14],"models":[15,24,29,51,75,147],"perform":[17],"on-par":[18],"with,":[19],"or":[20],"even":[21],"outperform,":[22],"hybrid":[23,67,143],"in":[25,31,80],"speech":[26],"recognition.":[27],"These":[28],"differ":[30],"their":[32,81],"designs,":[33],"and":[34,40,68,86,99,120,144],"as":[35],"such,":[36],"exhibit":[38,77],"diverse":[39],"complementary":[41],"error":[42],"patterns.":[43],"A":[44],"combination":[45,65,95],"between":[46,66],"the":[47,60,140],"predictions":[48],"of":[49,62,117,142],"these":[50],"therefore":[53],"yield":[54],"significant":[55,133],"gains.":[56],"This":[57],"paper":[58],"feasibility":[61],"performing":[63],"hypothesis-level":[64],"NN":[70,74,146],"models.":[71],"The":[72,129],"often":[76],"a":[78],"bias":[79],"posteriors":[82],"toward":[83],"short":[84],"hypotheses,":[85],"this":[87,107],"adversely":[89],"affect":[90],"Minimum":[91],"Bayes\u2019":[92],"Risk":[93],"(MBR)":[94],"methods.":[96],"MBR":[97],"training":[98],"length":[100],"normalisation":[101],"can":[102,135],"used":[104],"reduce":[106],"bias.":[108],"Models":[109],"are":[110],"trained":[111],"on":[112,122],"Microsoft\u2019s":[113],"75":[114],"thousand":[115],"hours":[116],"anonymised":[118],"data":[119],"evaluated":[121],"test":[123],"sets":[124],"with":[125],"1.8":[126],"million":[127],"words.":[128],"results":[130],"show":[131],"gains":[134],"obtained":[137],"by":[138],"combining":[139],"hypotheses":[141],"together.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}