{"id":"https://openalex.org/W3026287411","doi":"https://doi.org/10.21437/interspeech.2020-1780","title":"Enhancing Monotonic Multihead Attention for Streaming ASR","display_name":"Enhancing Monotonic Multihead Attention for Streaming ASR","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3026287411","doi":"https://doi.org/10.21437/interspeech.2020-1780","mag":"3026287411"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1780","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1780","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.09394","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"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":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"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":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2137","last_page":"2141"},"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":0.9997000098228455,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.8703534603118896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8062988519668579},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5858628749847412},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5762243270874023},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5686609745025635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44338059425354004},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4254404306411743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3688192069530487},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2227817177772522},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10541483759880066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07773074507713318}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8703534603118896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062988519668579},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5858628749847412},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5762243270874023},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5686609745025635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44338059425354004},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4254404306411743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3688192069530487},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2227817177772522},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10541483759880066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07773074507713318},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1780","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1780","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"},{"id":"pmh:oai:arXiv.org:2005.09394","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09394","pdf_url":"https://arxiv.org/pdf/2005.09394","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3026287411","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.09394.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.09394","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.09394","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.09394","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09394","pdf_url":"https://arxiv.org/pdf/2005.09394","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3026287411.pdf","grobid_xml":"https://content.openalex.org/works/W3026287411.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2250357346","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2605141709","https://openalex.org/W2745439869","https://openalex.org/W2750499125","https://openalex.org/W2799800213","https://openalex.org/W2913718171","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2946794439","https://openalex.org/W2949975180","https://openalex.org/W2952992734","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2963061963","https://openalex.org/W2963242190","https://openalex.org/W2963312585","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963827914","https://openalex.org/W2963828549","https://openalex.org/W2964272710","https://openalex.org/W2970565456","https://openalex.org/W2972818416","https://openalex.org/W2981696585","https://openalex.org/W2995428172","https://openalex.org/W2998814410","https://openalex.org/W3008191852","https://openalex.org/W3015194534","https://openalex.org/W3015654466","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3016167541","https://openalex.org/W3023277061"],"related_works":["https://openalex.org/W3097125541","https://openalex.org/W1828163288","https://openalex.org/W2963403868","https://openalex.org/W2963242190","https://openalex.org/W2127141656","https://openalex.org/W3015974384","https://openalex.org/W2972818416","https://openalex.org/W854541894","https://openalex.org/W3025165719","https://openalex.org/W2964272710","https://openalex.org/W2936774411","https://openalex.org/W2327501763","https://openalex.org/W3092122846","https://openalex.org/W2962780374","https://openalex.org/W2526425061","https://openalex.org/W2952992734","https://openalex.org/W2988394319","https://openalex.org/W2952329796","https://openalex.org/W2955646770","https://openalex.org/W2102654168"],"abstract_inverted_index":{"We":[0],"investigate":[1],"a":[2,59,77],"monotonic":[3,10,26],"multihead":[4,118],"attention":[5,11,27,109],"(MMA)":[6],"by":[7,74,105],"extending":[8],"hard":[9],"to":[12,66,87,91,116,127],"Transformer-based":[13],"automatic":[14],"speech":[15],"recognition":[16],"(ASR)":[17],"for":[18,96],"online":[19],"streaming":[20,23,130],"applications.":[21],"For":[22],"inference,":[24],"all":[25,42,53],"(MA)":[28],"heads":[29,43,55,80,90,95],"should":[30],"learn":[31,56,67],"proper":[32],"alignments":[33,57,68],"because":[34],"the":[35,45,117],"next":[36],"token":[37,47,102],"is":[38,114],"not":[39,52],"generated":[40],"until":[41],"detect":[44],"corresponding":[46],"boundaries.":[48],"However,":[49],"we":[50,70,85,121],"found":[51],"MA":[54,112],"with":[58],"na\u00efve":[60],"implementation.":[61],"To":[62],"encourage":[63],"every":[64],"head":[65,113],"properly,":[69],"propose":[71,86,122],"HeadDrop":[72],"regularization":[73],"masking":[75],"out":[76],"part":[78],"of":[79],"stochastically":[81],"during":[82],"training.":[83],"Furthermore,":[84],"prune":[88],"redundant":[89],"improve":[92],"consensus":[93],"among":[94],"boundary":[97],"detection":[98],"and":[99],"prevent":[100],"delayed":[101],"generation":[103],"caused":[104],"such":[106],"heads.":[107],"Chunkwise":[108],"on":[110],"each":[111],"extended":[115],"counterpart.":[119],"Finally,":[120],"head-synchronous":[123],"beam":[124],"search":[125],"decoding":[126],"guarantee":[128],"stable":[129],"inference.":[131]},"counts_by_year":[{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}