{"id":"https://openalex.org/W3015654466","doi":"https://doi.org/10.1109/icassp40776.2020.9054098","title":"Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR","display_name":"Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015654466","doi":"https://doi.org/10.1109/icassp40776.2020.9054098","mag":"3015654466"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","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":"Yashesh Gaur","raw_affiliation_strings":["Microsoft Speech and Language Group, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"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":"Yifan Gong","raw_affiliation_strings":["Microsoft Speech and Language Group, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040282669"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":5.5675,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96557362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6064","last_page":"6068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.8483158349990845},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7922059297561646},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7758193612098694},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.720112681388855},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5728054046630859},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.561522901058197},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5574286580085754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4835064709186554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.412004679441452},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3398757576942444},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24311348795890808},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07491913437843323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483158349990845},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7922059297561646},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7758193612098694},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.720112681388855},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5728054046630859},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.561522901058197},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5574286580085754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4835064709186554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.412004679441452},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3398757576942444},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24311348795890808},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07491913437843323},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1533416326","https://openalex.org/W1828163288","https://openalex.org/W1902237438","https://openalex.org/W1924770834","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2491408735","https://openalex.org/W2514969556","https://openalex.org/W2597757402","https://openalex.org/W2605141709","https://openalex.org/W2745439869","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2767601419","https://openalex.org/W2888884590","https://openalex.org/W2889068726","https://openalex.org/W2889163603","https://openalex.org/W2936123380","https://openalex.org/W2949975180","https://openalex.org/W2952992734","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963303028","https://openalex.org/W2963312585","https://openalex.org/W2963362078","https://openalex.org/W2963827914","https://openalex.org/W2963970535","https://openalex.org/W2964121744","https://openalex.org/W2964272710","https://openalex.org/W2972439411","https://openalex.org/W2972977747","https://openalex.org/W2972995428","https://openalex.org/W2997454826","https://openalex.org/W3007528493","https://openalex.org/W3016167541","https://openalex.org/W4294619417","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6723310180","https://openalex.org/W6735390525","https://openalex.org/W6735706088","https://openalex.org/W6745543685","https://openalex.org/W6746574493","https://openalex.org/W6747158283","https://openalex.org/W6752739165","https://openalex.org/W6763194437","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W2384362569","https://openalex.org/W4220731478","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Recently,":[0],"a":[1],"few":[2],"novel":[3],"streaming":[4,173],"attention-based":[5],"sequence-to-sequence":[6],"(S2S)":[7],"models":[8],"have":[9],"been":[10],"proposed":[11,143],"to":[12,27,33,47,78,168],"perform":[13],"online":[14],"speech":[15],"recognition":[16,154],"with":[17,99],"linear-time":[18],"decoding":[19],"complexity.":[20],"However,":[21],"in":[22,82,156],"these":[23],"models,":[24],"the":[25,34,73,80,84,87,90,100,107,121,128,135,148,153,160,170],"decisions":[26],"generate":[28],"tokens":[29],"are":[30,104],"delayed":[31],"compared":[32],"actual":[35],"acoustic":[36],"boundaries":[37],"since":[38],"their":[39],"unidirectional":[40],"encoders":[41],"lack":[42],"future":[43],"information.":[44],"This":[45],"leads":[46],"an":[48,117],"inevitable":[49],"latency":[50,119,131],"during":[51,64,120],"inference.":[52],"To":[53],"alleviate":[54],"this":[55],"issue":[56],"and":[57,86,96,124,150],"reduce":[58,147],"latency,":[59,149],"we":[60,110],"propose":[61],"several":[62],"strategies":[63],"training":[65],"by":[66],"leveraging":[67],"external":[68],"hard":[69],"alignments":[70,81],"extracted":[71],"from":[72],"hybrid":[74],"model.":[75],"We":[76,163],"investigate":[77],"utilize":[79],"both":[83],"encoder":[85,91],"decoder.":[88],"On":[89,106],"side,":[92,109],"(1)":[93],"multi-task":[94],"learning":[95],"(2)":[97],"pre-training":[98],"framewise":[101],"classification":[102],"task":[103,139],"studied.":[105],"decoder":[108,161],"(3)":[111],"remove":[112],"inappropriate":[113],"alignment":[114,122],"paths":[115],"beyond":[116],"acceptable":[118],"marginalization,":[123],"(4)":[125],"directly":[126],"min-imize":[127],"differentiable":[129],"expected":[130],"loss.":[132],"Experiments":[133],"on":[134,159],"Cortana":[136],"voice":[137],"search":[138],"demonstrate":[140],"that":[141],"our":[142],"methods":[144],"can":[145],"significantly":[146],"even":[151],"improve":[152],"accuracy":[155],"certain":[157],"cases":[158],"side.":[162],"also":[164],"present":[165],"some":[166],"analysis":[167],"understand":[169],"behaviors":[171],"of":[172],"S2S":[174],"models.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":16}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}