{"id":"https://openalex.org/W3096702180","doi":"https://doi.org/10.21437/interspeech.2020-1292","title":"Low Latency End-to-End Streaming Speech Recognition with a Scout Network","display_name":"Low Latency End-to-End Streaming Speech Recognition with a Scout Network","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096702180","doi":"https://doi.org/10.21437/interspeech.2020-1292","mag":"3096702180"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1292","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1292","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/A5101863385","display_name":"Chengyi Wang","orcid":"https://orcid.org/0000-0002-6780-9299"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyi Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft Research Asia, Beijing"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008578397","display_name":"Guoli Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoli Ye","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701575","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0003-0696-767X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Microsoft Research Asia, Beijing"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100701575"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":3.7037,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9434293,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2112","last_page":"2116"},"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.744536817073822},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7280762791633606},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.69408118724823},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6813266277313232},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6191357970237732},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5454027652740479},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.35171282291412354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27549028396606445},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11664849519729614},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11279547214508057},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07965144515037537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744536817073822},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7280762791633606},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.69408118724823},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6813266277313232},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6191357970237732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5454027652740479},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35171282291412354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27549028396606445},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11664849519729614},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11279547214508057},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07965144515037537},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1292","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1292","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":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1710082047","https://openalex.org/W1828163288","https://openalex.org/W2085628288","https://openalex.org/W2102113734","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2514969556","https://openalex.org/W2747874407","https://openalex.org/W2766219058","https://openalex.org/W2913718171","https://openalex.org/W2936774411","https://openalex.org/W2962826786","https://openalex.org/W2963414781","https://openalex.org/W2963979492","https://openalex.org/W2964110616","https://openalex.org/W2972439411","https://openalex.org/W2972818416","https://openalex.org/W2981696585","https://openalex.org/W2981857663","https://openalex.org/W3007433671","https://openalex.org/W3015457435","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3095189764","https://openalex.org/W4294619417","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W3196421258","https://openalex.org/W4404782863"],"abstract_inverted_index":{"The":[0],"attention-based":[1],"Transformer":[2,21,52],"model":[3,22,96],"has":[4],"achieved":[5],"promising":[6],"results":[7],"for":[8,51],"speech":[9],"recognition":[10,30,62,78],"(SR)":[11],"in":[12,16,38],"the":[13,17,20,67,77,81,86,90,93,98,108],"offline":[14],"mode.However,":[15],"streaming":[18,49],"mode,":[19],"usually":[23],"incurs":[24],"significant":[25],"latency":[26,106],"to":[27],"maintain":[28],"its":[29],"accuracy":[31],"when":[32],"applying":[33],"a":[34,46,57,61],"fixed-length":[35],"look-ahead":[36],"window":[37],"each":[39],"encoder":[40],"layer.In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"novel":[47],"low-latency":[48],"approach":[50],"models,":[53],"which":[54],"consists":[55],"of":[56,114],"scout":[58,64],"network":[59,65,79],"and":[60,110],"network.The":[63],"detects":[66],"whole":[68],"word":[69],"boundary":[70],"without":[71],"seeing":[72],"any":[73],"future":[74],"frames,":[75],"while":[76],"predicts":[80],"next":[82],"subword":[83],"by":[84],"utilizing":[85],"information":[87],"from":[88],"all":[89],"frames":[91],"before":[92],"predicted":[94],"boundary.Our":[95],"achieves":[97],"best":[99],"performance":[100],"(2.7/6.4WER)":[101],"with":[102],"only":[103],"639":[104],"ms":[105],"on":[107],"test-clean":[109],"test-other":[111],"data":[112],"sets":[113],"Librispeech.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}