{"id":"https://openalex.org/W3097973766","doi":"https://doi.org/10.21437/interspeech.2020-2638","title":"Exploring Transformers for Large-Scale Speech Recognition","display_name":"Exploring Transformers for Large-Scale Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097973766","doi":"https://doi.org/10.21437/interspeech.2020-2638","mag":"3097973766"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2638","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2638","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/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/A5022890229","display_name":"Changliang Liu","orcid":"https://orcid.org/0009-0005-8201-0871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changliang Liu","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":3.6799,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.94578579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5041","last_page":"5045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.984499990940094,"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":0.9763000011444092,"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/computer-science","display_name":"Computer science","score":0.6583123803138733},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5841249823570251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5784153938293457},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.21278920769691467},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2022610902786255},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07953870296478271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583123803138733},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5841249823570251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5784153938293457},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.21278920769691467},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2022610902786255},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07953870296478271}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2638","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2638","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2005708641","https://openalex.org/W2133564696","https://openalex.org/W2150355110","https://openalex.org/W2396384435","https://openalex.org/W2802023636","https://openalex.org/W2892009249","https://openalex.org/W2906625520","https://openalex.org/W2911291251","https://openalex.org/W2963542740","https://openalex.org/W2964084166","https://openalex.org/W2964089206","https://openalex.org/W2970290486","https://openalex.org/W2972818416","https://openalex.org/W2976556660","https://openalex.org/W2981661615","https://openalex.org/W2981857663","https://openalex.org/W3006827623","https://openalex.org/W3008191852","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3095189764","https://openalex.org/W4288024261","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2778699561","https://openalex.org/W2892009249"],"abstract_inverted_index":{"While":[0],"recurrent":[1],"neural":[2],"networks":[3],"still":[4],"largely":[5],"define":[6],"state-of-theart":[7],"speech":[8,68],"recognition":[9,69],"systems,":[10],"the":[11,24,51,61,66,100,105,116,137,141,146],"Transformer":[12],"network":[13],"has":[14],"been":[15,31],"proven":[16],"to":[17,49,115,136,152],"be":[18],"a":[19,34],"competitive":[20],"alternative,":[21],"especially":[22],"in":[23,33,65,140,145],"offline":[25,142],"condition.Most":[26],"studies":[27],"with":[28,154],"Transformers":[29,64,124],"have":[30,73],"constrained":[32],"relatively":[35],"small":[36],"scale":[37],"setting,":[38,70],"and":[39],"some":[40],"forms":[41],"of":[42,63,78],"data":[43,52],"argumentation":[44],"approaches":[45],"are":[46],"usually":[47],"applied":[48],"combat":[50],"sparsity":[53],"issue.In":[54],"this":[55],"paper,":[56],"we":[57,72,103,121],"aim":[58],"at":[59],"understanding":[60],"behaviors":[62],"large-scale":[67],"where":[71],"used":[74,107],"around":[75,127],"65,000":[76],"hours":[77],"training":[79,92],"data.We":[80],"investigated":[81],"various":[82],"aspects":[83],"on":[84],"scaling":[85],"up":[86],"Transformers,":[87],"including":[88],"model":[89],"initialization,":[90],"warmup":[91],"as":[93,95],"well":[94],"different":[96],"Layer":[97],"Normalization":[98],"strategies.In":[99],"streaming":[101,147],"condition,":[102],"compared":[104,135],"widely":[106],"attention":[108],"mask":[109],"based":[110],"future":[111],"context":[112],"lookahead":[113],"approach":[114],"Transformer-XL":[117,149],"network.From":[118],"our":[119],"experiments,":[120],"show":[122],"that":[123],"can":[125],"achieve":[126],"6%":[128],"relative":[129],"word":[130],"error":[131],"rate":[132],"(WER)":[133],"reduction":[134],"BLSTM":[138],"baseline":[139],"fashion,":[143,148],"while":[144],"is":[150],"comparable":[151],"LC-BLSTM":[153],"800":[155],"millisecond":[156],"latency":[157],"constraint.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}