{"id":"https://openalex.org/W2973040747","doi":"https://doi.org/10.21437/interspeech.2019-1952","title":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","display_name":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973040747","doi":"https://doi.org/10.21437/interspeech.2019-1952","mag":"2973040747"},"language":"es","primary_location":{"id":"doi:10.21437/interspeech.2019-1952","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research -Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research -Tokyo","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1616","last_page":"1620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9965000152587891,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8305343985557556},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7428081631660461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5995261073112488},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5018894672393799},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.49389082193374634},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4806596040725708},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.47959673404693604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44484102725982666},{"id":"https://openalex.org/keywords/spike","display_name":"Spike (software development)","score":0.4421645700931549},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4219546616077423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4216967225074768},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35870134830474854},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21188116073608398},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.09654480218887329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305343985557556},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7428081631660461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5995261073112488},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5018894672393799},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.49389082193374634},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4806596040725708},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.47959673404693604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44484102725982666},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.4421645700931549},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4219546616077423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4216967225074768},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35870134830474854},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21188116073608398},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.09654480218887329},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1952","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1533416326","https://openalex.org/W1736701665","https://openalex.org/W1810943226","https://openalex.org/W1821462560","https://openalex.org/W1904457459","https://openalex.org/W1922655562","https://openalex.org/W2058641082","https://openalex.org/W2102113734","https://openalex.org/W2134797427","https://openalex.org/W2143612262","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2402040300","https://openalex.org/W2508418541","https://openalex.org/W2515439472","https://openalex.org/W2521999726","https://openalex.org/W2593910181","https://openalex.org/W2597757402","https://openalex.org/W2739883972","https://openalex.org/W2745937416","https://openalex.org/W2747909401","https://openalex.org/W2786018489","https://openalex.org/W2884975363","https://openalex.org/W2888884590","https://openalex.org/W2889785444","https://openalex.org/W2892008152","https://openalex.org/W2913178639","https://openalex.org/W2963070863","https://openalex.org/W2963266252","https://openalex.org/W2963953073","https://openalex.org/W2964038834","https://openalex.org/W4253573210"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645"],"abstract_inverted_index":{"Conventional":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"systems":[5,29],"trained":[6,30],"from":[7,54,66,149,159],"frame-level":[8,41],"alignments":[9],"can":[10],"easily":[11],"leverage":[12],"posterior":[13,51,64,124],"fusion":[14,65,125],"to":[15,78,90,157],"improve":[16],"ASR":[17,28],"accuracy":[18],"and":[19,43,49,69,129],"build":[20],"a":[21,58,76,80,95,100],"better":[22],"single":[23,144],"model":[24,46,82,109,147],"with":[25,92,135],"knowledge":[26,70,130],"distillation.End-to-end":[27],"using":[31,169],"the":[32,106,115,138,143,153,162],"Connectionist":[33],"Temporal":[34],"Classification":[35],"(CTC)":[36],"loss":[37],"do":[38],"not":[39],"require":[40],"alignment":[42],"hence":[44],"simplify":[45],"training.However,":[47],"sparse":[48],"arbitrary":[50],"spike":[52,86,112],"timings":[53,87],"CTC":[55,73,81,98,127,133,146],"models":[56,68,103,128,134,151],"pose":[57],"new":[59],"set":[60],"of":[61,94,117,126],"challenges":[62],"in":[63,120],"multiple":[67,150],"distillation":[71,131],"between":[72,132],"models.We":[74],"propose":[75],"method":[77,119],"train":[79],"so":[83],"that":[84,104],"its":[85],"are":[88],"guided":[89],"align":[91],"those":[93],"pre-trained":[96],"guiding":[97,108],"model.As":[99],"result,":[101],"all":[102],"share":[105],"same":[107],"have":[110],"aligned":[111],"timings.We":[113],"show":[114],"advantage":[116],"our":[118],"various":[121],"scenarios":[122],"including":[123],"different":[136],"architectures.With":[137],"300-hour":[139],"Switchboard":[140],"training":[141],"data,":[142],"word":[145,154],"distilled":[148],"improved":[152],"error":[155],"rates":[156],"13.7%/23.1%":[158],"14.9%/24.1%":[160],"on":[161],"Hub5":[163],"2000":[164],"Switchboard/CallHome":[165],"test":[166],"sets":[167],"without":[168],"any":[170],"data":[171],"augmentation,":[172],"language":[173],"model,":[174],"or":[175],"complex":[176],"decoder.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}