{"id":"https://openalex.org/W3016120074","doi":"https://doi.org/10.1109/icassp40776.2020.9053578","title":"Distilling Attention Weights for CTC-Based ASR Systems","display_name":"Distilling Attention Weights for CTC-Based ASR Systems","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016120074","doi":"https://doi.org/10.1109/icassp40776.2020.9053578","mag":"3016120074"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053578","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":"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/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739550","display_name":"Hiroshi Sato","orcid":"https://orcid.org/0000-0001-6575-0396"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009756622","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0001-7442-4912"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109365728","display_name":"Yusuke Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Shinohara","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6894","last_page":"6898"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.9968000054359436,"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":0.8353076577186584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5921922326087952},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5678860545158386},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.558813750743866},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5273526310920715},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5259190797805786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5117756724357605},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5003340244293213},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43808573484420776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42683830857276917},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4206409752368927},{"id":"https://openalex.org/keywords/spike","display_name":"Spike (software development)","score":0.4130234718322754},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21195107698440552},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18309712409973145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353076577186584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5921922326087952},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5678860545158386},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.558813750743866},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5273526310920715},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5259190797805786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5117756724357605},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5003340244293213},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43808573484420776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42683830857276917},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4206409752368927},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.4130234718322754},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21195107698440552},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18309712409973145},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053578","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":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1631260214","https://openalex.org/W1677182931","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2183341477","https://openalex.org/W2288471100","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2746192915","https://openalex.org/W2888884590","https://openalex.org/W2889030467","https://openalex.org/W2913178639","https://openalex.org/W2936993002","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963403868","https://openalex.org/W2963736842","https://openalex.org/W2963920996","https://openalex.org/W2964121744","https://openalex.org/W2972582323","https://openalex.org/W2973040747","https://openalex.org/W4385245566","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6636811518","https://openalex.org/W6638523607","https://openalex.org/W6638749077","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6686164453","https://openalex.org/W6739901393","https://openalex.org/W6746497681"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263","https://openalex.org/W2504816413"],"abstract_inverted_index":{"We":[0,75],"present":[1],"a":[2,24,64,159],"novel":[3],"training":[4,57],"approach":[5],"for":[6,21,71,86,119,153],"connectionist":[7],"temporal":[8],"classification":[9],"(CTC)":[10],"-based":[11],"automatic":[12],"speech":[13],"recognition":[14],"(ASR)":[15],"systems.":[16],"CTC":[17,35,72,131,154,179],"models":[18,36,132,175],"are":[19],"promising":[20],"building":[22],"both":[23],"conventional":[25],"acoustic":[26],"model":[27,73,84,155],"and":[28,110,117,139],"an":[29,81],"end-to-end":[30],"(E2E)":[31,161],"ASR":[32,145],"model.":[33],"However,":[34],"make":[37],"it":[38,157],"difficult":[39],"to":[40,174],"capture":[41],"the":[42,56,88,91,98,101,104,111,126,130,169],"correct":[43],"timing":[44,50,108],"of":[45,100,103],"each":[46],"output":[47],"label":[48],"because":[49],"is":[51,97,151],"not":[52],"given":[53],"explicitly":[54],"in":[55,168],"data.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"new":[65],"auxiliary":[66],"task":[67],"with":[68],"frame-wise":[69],"targets":[70],"enhancement.":[74],"utilize":[76],"attention":[77,92,95,105,127],"weights":[78,106],"generated":[79],"by":[80],"attention-based":[82],"encoder-decoder":[83],"(S2S)":[85],"making":[87],"targets,":[89],"called":[90],"matrix.":[93],"The":[94],"matrix":[96,128],"sum":[99],"products":[102],"(spike":[107],"information)":[109],"corresponding":[112],"target":[113],"vectors":[114],"(probability":[115],"information),":[116],"used":[118],"S2S-to-CTC":[120],"knowledge":[121],"distillation":[122],"loss":[123],"computation.":[124],"Therefore,":[125],"makes":[129],"jointly":[133],"train-able":[134],"as":[135],"regards":[136],"spike":[137],"timings":[138],"their":[140],"posteriors.":[141],"Experiments":[142],"on":[143],"Japanese":[144],"tasks":[146],"demonstrate":[147],"that":[148],"our":[149],"proposal":[150],"effective":[152],"training;":[156],"achieves":[158],"10.2%":[160],"/":[162],"9.4%":[163],"(acoustic":[164],"model)":[165],"relative":[166],"reduction":[167],"character/kana-syllable":[170],"error":[171],"rates":[172],"compared":[173],"trained":[176],"using":[177],"only":[178],"loss.":[180]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}