{"id":"https://openalex.org/W3023277061","doi":"https://doi.org/10.21437/interspeech.2020-1069","title":"CTC-Synchronous Training for Monotonic Attention Model","display_name":"CTC-Synchronous Training for Monotonic Attention Model","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3023277061","doi":"https://doi.org/10.21437/interspeech.2020-1069","mag":"3023277061"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1069","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1069","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/2005.04712","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"571","last_page":"575"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958999752998352,"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":0.9943000078201294,"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":0.758844256401062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7369964122772217},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.7151058316230774},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6526684761047363},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6238274574279785},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6094054579734802},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5889443159103394},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5786349177360535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5324500799179077},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4500475525856018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4355214238166809},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13621234893798828},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11700358986854553},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06861895322799683}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.758844256401062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369964122772217},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.7151058316230774},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6526684761047363},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6238274574279785},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6094054579734802},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5889443159103394},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5786349177360535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5324500799179077},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4500475525856018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4355214238166809},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13621234893798828},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11700358986854553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06861895322799683},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1069","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1069","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:2005.04712","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.04712","pdf_url":"https://arxiv.org/pdf/2005.04712","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":"","raw_type":"text"},{"id":"mag:3023277061","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2005.04712","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.2005.04712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.04712","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:2005.04712","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.04712","pdf_url":"https://arxiv.org/pdf/2005.04712","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023277061.pdf","grobid_xml":"https://content.openalex.org/works/W3023277061.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2250357346","https://openalex.org/W2407080277","https://openalex.org/W2605141709","https://openalex.org/W2631415506","https://openalex.org/W2739427748","https://openalex.org/W2746192915","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2949975180","https://openalex.org/W2962784628","https://openalex.org/W2963240019","https://openalex.org/W2963827914","https://openalex.org/W2964084166","https://openalex.org/W2964272710","https://openalex.org/W2970971581","https://openalex.org/W2972818416","https://openalex.org/W2972977747","https://openalex.org/W2998814410","https://openalex.org/W3007073761","https://openalex.org/W3007528493","https://openalex.org/W3008191852","https://openalex.org/W3008870153","https://openalex.org/W3015654466","https://openalex.org/W3016167541","https://openalex.org/W3018242354"],"related_works":["https://openalex.org/W3094759821","https://openalex.org/W3104881680","https://openalex.org/W2625225737","https://openalex.org/W2989576480","https://openalex.org/W2970045405","https://openalex.org/W2024085883","https://openalex.org/W2739688273","https://openalex.org/W2119774882","https://openalex.org/W3030128163","https://openalex.org/W2155607551","https://openalex.org/W3186513069","https://openalex.org/W2970076840","https://openalex.org/W3175321423","https://openalex.org/W3041514087","https://openalex.org/W2955019563","https://openalex.org/W3213956596","https://openalex.org/W2963403868","https://openalex.org/W3044783778","https://openalex.org/W2773728868","https://openalex.org/W2407351779"],"abstract_inverted_index":{"Monotonic":[0],"chunkwise":[1],"attention":[2],"(MoChA)":[3],"has":[4],"been":[5],"studied":[6],"for":[7,130,146],"the":[8,33,44,49,88,92,102,110,115,123,141],"online":[9],"streaming":[10],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"based":[15],"on":[16],"a":[17,84],"sequence-to-sequence":[18],"framework.":[19],"In":[20],"contrast":[21],"to":[22,40,54,73],"connectionist":[23],"temporal":[24],"classification":[25],"(CTC),":[26],"backward":[27],"probabilities":[28],"cannot":[29],"be":[30],"leveraged":[31],"in":[32,43,48,67],"alignment":[34],"marginalization":[35],"process":[36],"during":[37],"training":[38,65],"due":[39],"left-to-right":[41],"dependency":[42],"decoder.":[45,93],"This":[46],"results":[47],"error":[50],"propagation":[51],"of":[52,114,144],"alignments":[53,72,80],"subsequent":[55],"token":[56],"generation.":[57],"To":[58],"address":[59],"this":[60],"problem,":[61],"we":[62],"propose":[63],"CTC-synchronous":[64],"(CTC-ST),":[66],"which":[68],"MoChA":[69,106],"uses":[70],"CTC":[71,79,85],"learn":[74],"optimal":[75],"monotonic":[76],"alignments.":[77,111],"Reference":[78],"are":[81,107],"extracted":[82],"from":[83,105],"branch":[86],"sharing":[87],"same":[89],"encoder":[90],"with":[91,109],"The":[94],"entire":[95],"model":[96],"is":[97],"jointly":[98],"optimized":[99],"so":[100],"that":[101,122,136],"expected":[103],"boundaries":[104],"synchronized":[108],"Experimental":[112],"evaluations":[113],"TEDLIUM":[116],"release-2":[117],"and":[118],"Librispeech":[119],"corpora":[120],"show":[121,135],"proposed":[124],"method":[125],"significantly":[126],"improves":[127],"recognition,":[128],"especially":[129],"long":[131],"utterances.":[132],"We":[133],"also":[134],"CTC-ST":[137],"can":[138],"bring":[139],"out":[140],"full":[142],"potential":[143],"SpecAugment":[145],"MoChA.":[147]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}