{"id":"https://openalex.org/W3133822476","doi":"https://doi.org/10.1109/taslp.2021.3133217","title":"Alignment Knowledge Distillation for Online Streaming Attention-Based Speech Recognition","display_name":"Alignment Knowledge Distillation for Online Streaming Attention-Based Speech Recognition","publication_year":2021,"publication_date":"2021-12-07","ids":{"openalex":"https://openalex.org/W3133822476","doi":"https://doi.org/10.1109/taslp.2021.3133217","mag":"3133822476"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3133217","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3133217","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09640576.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09640576.pdf","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0610-1251","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2686-2296","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2284,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82522049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"1371","last_page":"1385"},"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":0.9994999766349792,"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":0.9993000030517578,"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":0.8487844467163086},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.700829803943634},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.683131754398346},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6426994800567627},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6231157779693604},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5743192434310913},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5618194341659546},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5008804798126221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4623938798904419},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4378575384616852},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41010552644729614},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3466123342514038},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08316829800605774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8487844467163086},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.700829803943634},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.683131754398346},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6426994800567627},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6231157779693604},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5743192434310913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5618194341659546},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5008804798126221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4623938798904419},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4378575384616852},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41010552644729614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3466123342514038},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08316829800605774},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3133217","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3133217","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09640576.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0005792082","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/281688","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3133217","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3133217","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09640576.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G2363020693","display_name":"A Study on Multi-modal Automatic Simultaneous Interpretation System and Evaluation Method","funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8019678971","display_name":"End-to-End Model for Task-Independent Speech Understanding and Dialogue","funder_award_id":"20H00602","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3133822476.pdf","grobid_xml":"https://content.openalex.org/works/W3133822476.grobid-xml"},"referenced_works_count":145,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1533416326","https://openalex.org/W1810943226","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1902237438","https://openalex.org/W1991646969","https://openalex.org/W2089629691","https://openalex.org/W2119631826","https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2142416747","https://openalex.org/W2144499799","https://openalex.org/W2183341477","https://openalex.org/W2250357346","https://openalex.org/W2291513470","https://openalex.org/W2325237720","https://openalex.org/W2327501763","https://openalex.org/W2394671344","https://openalex.org/W2404511972","https://openalex.org/W2407080277","https://openalex.org/W2491408735","https://openalex.org/W2510616059","https://openalex.org/W2514969556","https://openalex.org/W2515439472","https://openalex.org/W2526425061","https://openalex.org/W2605141709","https://openalex.org/W2647484625","https://openalex.org/W2745439869","https://openalex.org/W2746192915","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2888909726","https://openalex.org/W2888930363","https://openalex.org/W2889068726","https://openalex.org/W2889129739","https://openalex.org/W2892008152","https://openalex.org/W2911544293","https://openalex.org/W2913178639","https://openalex.org/W2915977493","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2949975180","https://openalex.org/W2962742956","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963158258","https://openalex.org/W2963312585","https://openalex.org/W2963382687","https://openalex.org/W2963403868","https://openalex.org/W2963681135","https://openalex.org/W2963729263","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2964038834","https://openalex.org/W2964084166","https://openalex.org/W2964121744","https://openalex.org/W2964272710","https://openalex.org/W2972356804","https://openalex.org/W2972439411","https://openalex.org/W2972702018","https://openalex.org/W2972818416","https://openalex.org/W2972837679","https://openalex.org/W2972977747","https://openalex.org/W2973040747","https://openalex.org/W2981696585","https://openalex.org/W2997454826","https://openalex.org/W3007073761","https://openalex.org/W3007227084","https://openalex.org/W3007328579","https://openalex.org/W3007528493","https://openalex.org/W3008174054","https://openalex.org/W3008191852","https://openalex.org/W3008870153","https://openalex.org/W3008898571","https://openalex.org/W3012641541","https://openalex.org/W3015190365","https://openalex.org/W3015194534","https://openalex.org/W3015315932","https://openalex.org/W3015654466","https://openalex.org/W3015927303","https://openalex.org/W3015974384","https://openalex.org/W3016120074","https://openalex.org/W3016167541","https://openalex.org/W3016234571","https://openalex.org/W3018242354","https://openalex.org/W3025165719","https://openalex.org/W3027656574","https://openalex.org/W3034729383","https://openalex.org/W3048407879","https://openalex.org/W3082041631","https://openalex.org/W3092318106","https://openalex.org/W3094759821","https://openalex.org/W3094957294","https://openalex.org/W3095189764","https://openalex.org/W3095311338","https://openalex.org/W3095950464","https://openalex.org/W3095996511","https://openalex.org/W3096123040","https://openalex.org/W3096318498","https://openalex.org/W3096518646","https://openalex.org/W3096524176","https://openalex.org/W3096702180","https://openalex.org/W3097125541","https://openalex.org/W3097777922","https://openalex.org/W3128478537","https://openalex.org/W3132621519","https://openalex.org/W3141756469","https://openalex.org/W3145511196","https://openalex.org/W3148654612","https://openalex.org/W3149509723","https://openalex.org/W3160766462","https://openalex.org/W3161080229","https://openalex.org/W3162649911","https://openalex.org/W3163203022","https://openalex.org/W3163213339","https://openalex.org/W3163907627","https://openalex.org/W3196784225","https://openalex.org/W3197479040","https://openalex.org/W3197956343","https://openalex.org/W3198260227","https://openalex.org/W4299435467","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6638523607","https://openalex.org/W6677812694","https://openalex.org/W6685711979","https://openalex.org/W6691509046","https://openalex.org/W6701498492","https://openalex.org/W6723310180","https://openalex.org/W6735706088","https://openalex.org/W6739612715","https://openalex.org/W6739901393","https://openalex.org/W6745543685","https://openalex.org/W6747158283","https://openalex.org/W6769647859","https://openalex.org/W6775139554","https://openalex.org/W6779469704","https://openalex.org/W6790121257","https://openalex.org/W6791545039"],"related_works":["https://openalex.org/W4389115113","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W3001710912","https://openalex.org/W4376480820","https://openalex.org/W3155891479"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"an":[3,38,135],"efficient":[4],"training":[5,66,89,119],"method":[6,149,188],"for":[7,100],"online":[8,39],"streaming":[9,40,70],"attention-based":[10,160],"encoder-decoder":[11],"(AED)":[12],"automatic":[13],"speech":[14,61,203],"recognition":[15,191],"(ASR)":[16],"systems.":[17],"AED":[18],"models":[19,43],"have":[20,33],"achieved":[21],"competitive":[22],"performance":[23],"in":[24,76,91,154],"offline":[25],"scenarios":[26],"by":[27],"jointly":[28],"optimizing":[29],"all":[30],"components.":[31],"They":[32],"recently":[34],"been":[35],"extended":[36],"to":[37,103,108,121,127,141,158,174,199],"framework":[41],"via":[42],"such":[44],"as":[45,97,167],"monotonie":[46,111],"chunkwise":[47],"attention":[48,53],"(MoChA).":[49],"However,":[50],"the":[51,64,123,138,143,147,155,159,186,225],"elaborate":[52],"calculation":[54],"process":[55],"is":[56,204],"not":[57],"robust":[58],"against":[59],"long-form":[60,200],"utterances.":[62],"Moreover,":[63,146],"sequence-level":[65],"objective":[67,120],"and":[68,193,201,222,234],"time-restricted":[69],"encoder":[71,136,144],"cause":[72],"a":[73,98,105,116,179,218,229],"nonnegligible":[74],"delay":[75],"token":[77,101],"emission":[78,194],"during":[79],"inference.":[80],"To":[81],"address":[82],"these":[83],"problems,":[84],"we":[85],"propose":[86],"CTC":[87,93,132,156,173],"synchronous":[88],"(CTC-ST),":[90],"which":[92],"alignments":[94],"are":[95],"leveraged":[96],"reference":[99],"boundaries":[102,124],"enable":[104],"MoChA":[106,126,139],"model":[107,133,140],"learn":[109],"optimal":[110],"input-output":[112],"alignments.":[113],"We":[114,207],"formulate":[115],"purely":[117],"end-to-end":[118],"synchronize":[122],"of":[125,129,169,181,232],"those":[128],"CTC.":[130],"The":[131,197],"shares":[134],"with":[137,210],"enhance":[142],"representation.":[145],"proposed":[148,187],"provides":[150],"alignment":[151,170,215,240],"information":[152],"learned":[153],"branch":[157],"decoder.":[161],"Therefore,":[162],"CTC-ST":[163,209,226],"can":[164,227],"be":[165],"regarded":[166],"self-distillation":[168],"knowledge":[171,216],"from":[172,217],"MoChA.":[175],"Experimental":[176],"evaluations":[177],"on":[178,238],"variety":[180],"benchmark":[182],"datasets":[183],"show":[184,223],"that":[185,213,224],"significantly":[189],"reduces":[190],"errors":[192],"latency":[195,235],"simultaneously.":[196],"robustness":[198],"noisy":[202],"also":[205],"demonstrated.":[206],"compare":[208],"several":[211],"methods":[212],"distill":[214],"hybrid":[219],"ASR":[220],"system":[221],"achieve":[228],"comparable":[230],"tradeoff":[231],"accuracy":[233],"without":[236],"relying":[237],"external":[239],"information.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}