{"id":"https://openalex.org/W2913588326","doi":"https://doi.org/10.1109/slt.2018.8639545","title":"Efficient Building Strategy with Knowledge Distillation for Small-Footprint Acoustic Models","display_name":"Efficient Building Strategy with Knowledge Distillation for Small-Footprint Acoustic Models","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913588326","doi":"https://doi.org/10.1109/slt.2018.8639545","mag":"2913588326"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5076754533","display_name":"Hiroki Kanagawa","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":"Hiroki Kanagawa","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/A5078234159","display_name":"Kiyoaki Matsui","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":"Kiyoaki Matsui","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/A5067107593","display_name":"Takaaki Fukutomi","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":"Takaaki Fukutomi","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/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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067744302","display_name":"Yoshikazu Yamaguchi","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":"Yoshikazu Yamaguchi","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/A5101532289","display_name":"Manabu Okamoto","orcid":"https://orcid.org/0009-0004-3612-9639"},"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":"Manabu Okamoto","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/A5067237053","display_name":"Yushi Aono","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":"Yushi Aono","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"21","last_page":"28"},"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007057905197144},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6624863147735596},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.603706419467926},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5393597483634949},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5085197687149048},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4892735183238983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44817695021629333},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44280073046684265},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4350054860115051},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4291076362133026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4157971739768982},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41328591108322144},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39293450117111206},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32137972116470337},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.16944438219070435},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15783941745758057},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10632175207138062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007057905197144},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6624863147735596},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.603706419467926},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5393597483634949},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5085197687149048},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4892735183238983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44817695021629333},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44280073046684265},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4350054860115051},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4291076362133026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4157971739768982},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41328591108322144},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39293450117111206},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32137972116470337},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.16944438219070435},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15783941745758057},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10632175207138062},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1735150698","https://openalex.org/W1799366690","https://openalex.org/W1821462560","https://openalex.org/W1995562189","https://openalex.org/W2058641082","https://openalex.org/W2064675550","https://openalex.org/W2084910356","https://openalex.org/W2138889249","https://openalex.org/W2143545157","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2182629226","https://openalex.org/W2247516327","https://openalex.org/W2288645994","https://openalex.org/W2294543795","https://openalex.org/W2402040300","https://openalex.org/W2481916066","https://openalex.org/W2508418541","https://openalex.org/W2549177447","https://openalex.org/W2586348040","https://openalex.org/W2586441793","https://openalex.org/W2590276831","https://openalex.org/W2680270903","https://openalex.org/W2747909401","https://openalex.org/W2888867390","https://openalex.org/W2890012642","https://openalex.org/W2949964376","https://openalex.org/W2963124866","https://openalex.org/W2963523217","https://openalex.org/W2963643655","https://openalex.org/W2963674932","https://openalex.org/W2963864497","https://openalex.org/W6638444622","https://openalex.org/W6638523607","https://openalex.org/W6638632666","https://openalex.org/W6696912008","https://openalex.org/W6712847557"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W3137434606","https://openalex.org/W4372263373"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4,130],"a":[5,78,88],"novel":[6],"training":[7,179],"strategy":[8],"for":[9],"deep":[10],"neural":[11],"network":[12],"(DNN)":[13],"based":[14],"small-footprint":[15],"acoustic":[16,66],"models.":[17],"The":[18],"accuracy":[19],"of":[20,35,41],"DNN-based":[21,60],"automatic":[22],"speech":[23,155],"recognition":[24,49],"(ASR)":[25],"systems":[26],"can":[27],"be":[28],"greatly":[29],"improved":[30],"by":[31],"leveraging":[32],"large":[33,99,118],"amounts":[34],"data":[36,156],"to":[37,47,57,86,102,125,139],"improve":[38],"the":[39,68,92,98,107,117,126,141,144,173],"level":[40],"expression.":[42],"DNNs":[43],"use":[44],"many":[45],"parameters":[46],"enhance":[48],"performance.":[50],"Unfortunately,":[51],"resource-constrained":[52,182],"local":[53],"devices":[54],"are":[55],"unable":[56],"run":[58],"complex":[59],"ASR":[61],"systems.":[62],"For":[63],"building":[64],"compact":[65,89,104,127],"models,":[67],"knowledge":[69],"distillation":[70],"(KD)":[71],"approach":[72,176],"is":[73],"often":[74],"used.":[75],"KD":[76,94,133,175],"uses":[77,135],"large,":[79],"well-trained":[80],"model":[81,100,119],"that":[82,116,134,164],"outputs":[83,101],"target":[84],"labels":[85],"train":[87,103],"model.":[90,128],"However,":[91],"standard":[93],"cannot":[95],"fully":[96],"utilize":[97],"models":[105,166],"because":[106],"soft":[108],"logits":[109],"provide":[110],"only":[111],"rough":[112],"information.":[113],"We":[114,129,149],"assume":[115],"must":[120],"give":[121],"more":[122],"useful":[123],"hints":[124],"an":[131],"advanced":[132],"mean":[136],"squared":[137],"error":[138,170],"minimize":[140],"discrepancies":[142],"between":[143],"final":[145],"hidden":[146],"layer":[147],"outputs.":[148],"evaluate":[150],"our":[151,165],"proposal":[152],"on":[153,180],"recorded":[154],"sets":[157],"assuming":[158],"car-and":[159],"home-use":[160],"scenarios,":[161],"and":[162],"show":[163],"achieve":[167],"lower":[168],"character":[169],"rates":[171],"than":[172],"conventional":[174],"or":[177],"from-scratch":[178],"computation":[181],"devices.":[183]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}