{"id":"https://openalex.org/W3096686110","doi":"https://doi.org/10.21437/interspeech.2020-2361","title":"Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition","display_name":"Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096686110","doi":"https://doi.org/10.21437/interspeech.2020-2361","mag":"3096686110"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2361","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/A5032912499","display_name":"Wenyong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wenyong Huang","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023202964","display_name":"Wenchao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wenchao Hu","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100373718","display_name":"Xiao Chen","orcid":"https://orcid.org/0000-0002-3290-507X"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159102"],"apc_list":null,"apc_paid":null,"fwci":5.5529,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96628628,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9959999918937683,"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":0.9930999875068665,"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":0.5937316417694092},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5719267725944519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5311333537101746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5061137080192566},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.48790261149406433},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.25233274698257446},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20839250087738037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13006386160850525},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06447768211364746}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5937316417694092},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5719267725944519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5311333537101746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5061137080192566},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.48790261149406433},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.25233274698257446},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20839250087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13006386160850525},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06447768211364746}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2361","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":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2133564696","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2729190387","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2945697643","https://openalex.org/W2962760690","https://openalex.org/W2963045354","https://openalex.org/W2963088785","https://openalex.org/W2963250244","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2976556660","https://openalex.org/W2981857663","https://openalex.org/W3008191852","https://openalex.org/W3015194534","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W4288088457","https://openalex.org/W4294619417","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2983157715","https://openalex.org/W2778699561","https://openalex.org/W3007625080","https://openalex.org/W2971982237","https://openalex.org/W2938947737","https://openalex.org/W2312526371","https://openalex.org/W2954695182","https://openalex.org/W4224917401","https://openalex.org/W4303519918","https://openalex.org/W2600628583"],"abstract_inverted_index":{"Transformer":[0,51,62,83,162],"has":[1],"achieved":[2,172],"competitive":[3,142],"performance":[4,143,155],"against":[5],"state-of-the-art":[6],"end-to-end":[7],"models":[8],"in":[9,57,123],"automatic":[10],"speech":[11],"recognition":[12],"(ASR),":[13],"and":[14,42,164,170,181],"requires":[15],"significantly":[16],"less":[17],"training":[18],"time":[19],"than":[20],"RNN-based":[21],"models.The":[22,154],"original":[23],"Transformer,":[24],"with":[25,84,111,173],"encoderdecoder":[26],"architecture,":[27,137],"is":[28,98,156,171],"only":[29],"suitable":[30,63],"for":[31,64,93,130],"offline":[32],"ASR.It":[33],"relies":[34],"on":[35,144,149],"an":[36],"attention":[37],"mechanism":[38],"to":[39,75,100,125,158],"learn":[40,76],"alignments,":[41],"encodes":[43],"input":[44],"audio":[45,78],"bidirectionally.The":[46],"high":[47],"computation":[48,103,128],"cost":[49,129],"of":[50,120],"decoding":[52,132],"also":[53,110],"limits":[54],"its":[55],"use":[56],"production":[58],"streaming":[59,65,167],"systems.To":[60],"make":[61],"ASR,":[66],"we":[67,80,105,116],"explore":[68],"Transducer":[69,163],"framework":[70],"as":[71],"a":[72],"streamable":[73,161],"way":[74],"alignments.For":[77],"encoding,":[79],"apply":[81],"unidirectional":[82],"interleaved":[85,88,113],"convolution":[86,89,114],"layers.The":[87],"layers":[90],"are":[91],"used":[92],"modeling":[94],"future":[95],"context":[96,122],"which":[97],"important":[99],"performance.To":[101],"reduce":[102],"cost,":[104],"gradually":[106],"downsample":[107],"acoustic":[108],"input,":[109],"the":[112,118],"layers.Moreover,":[115],"limit":[117],"length":[119],"history":[121],"self-attention":[124],"maintain":[126],"constant":[127],"each":[131],"step.We":[133],"show":[134],"that":[135],"this":[136],"named":[138],"Conv-Transformer":[139],"Transducer,":[140],"achieves":[141],"LibriSpeech":[145],"dataset":[146],"(3.6%":[147],"WER":[148],"test-clean)":[150],"without":[151],"external":[152],"language":[153],"comparable":[157],"previously":[159],"published":[160],"strong":[165],"hybrid":[166],"ASR":[168],"systems,":[169],"smaller":[174],"look-ahead":[175],"window":[176],"(140":[177],"ms),":[178],"fewer":[179],"parameters":[180],"lower":[182],"frame":[183],"rate.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}