{"id":"https://openalex.org/W4319862663","doi":"https://doi.org/10.1109/slt54892.2023.10022581","title":"Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition","display_name":"Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862663","doi":"https://doi.org/10.1109/slt54892.2023.10022581"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022581","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5016783920","display_name":"Ji Won Yoon","orcid":"https://orcid.org/0000-0001-8631-4489"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Ji Won Yoon","raw_affiliation_strings":["Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231"]},{"raw_affiliation_string":"Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003903797","display_name":"Beom Jun Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Beom Jun Woo","raw_affiliation_strings":["Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231"]},{"raw_affiliation_string":"Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176510","display_name":"Sunghwan Ahn","orcid":"https://orcid.org/0009-0001-6799-6821"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Sunghwan Ahn","raw_affiliation_strings":["Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231"]},{"raw_affiliation_string":"Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103052875","display_name":"Hyeonseung Lee","orcid":"https://orcid.org/0000-0001-6997-205X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Hyeonseung Lee","raw_affiliation_strings":["Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231"]},{"raw_affiliation_string":"Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231"]},{"raw_affiliation_string":"Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1779,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89357948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"286"},"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":0.9987000226974487,"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":0.9986000061035156,"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/pipeline","display_name":"Pipeline (software)","score":0.7885357737541199},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7677520513534546},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646406292915344},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.712090015411377},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5494458675384521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5405295491218567},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5261796712875366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49744585156440735},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.466196209192276},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4652676582336426},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46288251876831055},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44901981949806213},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4263477325439453},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37855690717697144},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3582804799079895},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08805131912231445},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08557412028312683},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07827216386795044}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7885357737541199},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7677520513534546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646406292915344},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.712090015411377},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5494458675384521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5405295491218567},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5261796712875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49744585156440735},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.466196209192276},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4652676582336426},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46288251876831055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44901981949806213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4263477325439453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37855690717697144},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3582804799079895},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08805131912231445},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08557412028312683},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07827216386795044},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022581","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2291513470","https://openalex.org/W2402040300","https://openalex.org/W2508418541","https://openalex.org/W2711861986","https://openalex.org/W2747909401","https://openalex.org/W2752782242","https://openalex.org/W2892008152","https://openalex.org/W2901739041","https://openalex.org/W2913178639","https://openalex.org/W2936993002","https://openalex.org/W2945697643","https://openalex.org/W2963736842","https://openalex.org/W2963864497","https://openalex.org/W2973040747","https://openalex.org/W2973215447","https://openalex.org/W3015537910","https://openalex.org/W3046667470","https://openalex.org/W3097882114","https://openalex.org/W3141854550","https://openalex.org/W3156828761","https://openalex.org/W3162249256","https://openalex.org/W6629717138","https://openalex.org/W6638523607","https://openalex.org/W6679855610","https://openalex.org/W6684665197","https://openalex.org/W6697339895","https://openalex.org/W6756104738","https://openalex.org/W6762625080","https://openalex.org/W6774835902","https://openalex.org/W6792376965"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Recently,":[0],"the":[1,12,18,26,29,59,72,80,84,89,93,97,102,109,124,135],"advance":[2],"in":[3,11],"deep":[4],"learning":[5],"has":[6,35],"brought":[7],"a":[8,49,64],"considerable":[9],"improvement":[10],"end-to-end":[13,27],"speech":[14],"recognition":[15],"field,":[16],"simplifying":[17],"traditional":[19],"pipeline":[20],"while":[21],"producing":[22],"promising":[23],"results.":[24],"Among":[25],"models,":[28],"connectionist":[30],"temporal":[31],"classification":[32],"(CTC)-based":[33],"model":[34,117],"attracted":[36],"research":[37],"interest":[38],"due":[39],"to":[40,53,83,108,132],"its":[41],"non-autoregressive":[42],"nature.":[43],"However,":[44],"such":[45],"CTC":[46,73,86],"models":[47],"require":[48],"heavy":[50],"computational":[51,60],"cost":[52],"achieve":[54],"outstanding":[55],"performance.":[56],"To":[57],"mitigate":[58],"burden,":[61],"we":[62,99],"propose":[63],"simple":[65],"yet":[66],"effective":[67],"knowledge":[68,82],"distillation":[69],"(KD)":[70],"for":[71],"framework,":[74],"namely":[75],"Inter-KD,":[76],"that":[77,101],"additionally":[78],"transfers":[79],"teacher's":[81],"intermediate":[85],"layers":[87],"of":[88],"student":[90],"network.":[91],"From":[92],"experimental":[94],"results":[95],"on":[96,134],"LibriSpeech,":[98],"verify":[100],"Inter-KD":[103,122],"shows":[104],"better":[105],"achievements":[106],"compared":[107],"conventional":[110],"KD":[111],"methods.":[112],"Without":[113],"using":[114],"any":[115],"language":[116],"(LM)":[118],"and":[119],"data":[120],"augmentation,":[121],"improves":[123],"word":[125],"error":[126],"rate":[127],"(WER)":[128],"performance":[129],"from":[130],"8.85%":[131],"6.30%":[133],"test-clean.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}