{"id":"https://openalex.org/W4392904386","doi":"https://doi.org/10.1109/icassp48485.2024.10446721","title":"AdaMER-CTC: Connectionist Temporal Classification with Adaptive Maximum Entropy Regularization for Automatic Speech Recognition","display_name":"AdaMER-CTC: Connectionist Temporal Classification with Adaptive Maximum Entropy Regularization for Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904386","doi":"https://doi.org/10.1109/icassp48485.2024.10446721"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5112980303","display_name":"SooHwan Eom","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"SooHwan Eom","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031585399","display_name":"Eunseop Yoon","orcid":"https://orcid.org/0000-0002-5580-5354"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunseop Yoon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103277375","display_name":"Hee Suk Yoon","orcid":"https://orcid.org/0000-0003-2115-8459"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hee Suk Yoon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Korea University,Seoul,Republic of Korea","Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112980303"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.5366,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8960689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12707","last_page":"12711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7098644375801086},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7007066607475281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5604772567749023},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5445440411567688},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5220006704330444},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5111220479011536},{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"Entropy maximization","score":0.4960106313228607},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4754592776298523},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.46176260709762573},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.45781081914901733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4384766221046448},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4105478525161743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37401914596557617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33063265681266785},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1625649333000183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15996119379997253},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08634158968925476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098644375801086},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7007066607475281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5604772567749023},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5445440411567688},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5220006704330444},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5111220479011536},{"id":"https://openalex.org/C127233936","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Entropy maximization","level":3,"score":0.4960106313228607},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4754592776298523},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.46176260709762573},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.45781081914901733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4384766221046448},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4105478525161743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37401914596557617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33063265681266785},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1625649333000183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15996119379997253},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08634158968925476},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G3450174791","display_name":null,"funder_award_id":"2022-0-00184","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6758007335","display_name":null,"funder_award_id":"2022-0-00184","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2032558547","https://openalex.org/W2122585011","https://openalex.org/W2127141656","https://openalex.org/W2152563462","https://openalex.org/W2183341477","https://openalex.org/W2765097853","https://openalex.org/W2781726626","https://openalex.org/W2904246096","https://openalex.org/W2963403664","https://openalex.org/W2964038834","https://openalex.org/W3035512170","https://openalex.org/W3097777922","https://openalex.org/W3167895882","https://openalex.org/W4212774754","https://openalex.org/W4297798436","https://openalex.org/W6687566353","https://openalex.org/W6692846177","https://openalex.org/W6732696085","https://openalex.org/W6747473740","https://openalex.org/W6754747464","https://openalex.org/W6757592117","https://openalex.org/W6796656850"],"related_works":["https://openalex.org/W3102188974","https://openalex.org/W3004810941","https://openalex.org/W4287870705","https://openalex.org/W3199097846","https://openalex.org/W624081655","https://openalex.org/W2951493954","https://openalex.org/W2576492542","https://openalex.org/W1952656308","https://openalex.org/W2073182819","https://openalex.org/W2267645079"],"abstract_inverted_index":{"In":[0,80],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems,":[5],"a":[6,21,29,63,90],"recurring":[7],"obstacle":[8],"is":[9],"the":[10,48,68,71,95,101,120],"generation":[11],"of":[12,24,97],"narrowly":[13],"focused":[14],"output":[15],"distributions.":[16],"This":[17,104],"phenomenon":[18],"emerges":[19],"as":[20,115],"side":[22],"effect":[23],"Connectionist":[25],"Temporal":[26],"Classification":[27],"(CTC),":[28],"robust":[30],"sequence":[31,39],"learning":[32],"tool":[33],"that":[34,92,114],"utilizes":[35],"dynamic":[36],"programming":[37],"for":[38],"mapping.":[40],"While":[41],"earlier":[42],"efforts":[43],"have":[44],"tried":[45],"to":[46,57],"combine":[47],"CTC":[49],"loss":[50],"with":[51],"an":[52],"entropy":[53,98],"maximization":[54],"regularization":[55,69,99],"term":[56,66],"mitigate":[58],"this":[59,81],"issue,":[60],"they":[61],"employed":[62],"constant":[64],"weighting":[65],"on":[67],"during":[70],"training,":[72],"which":[73],"we":[74,83],"find":[75],"may":[76],"not":[77,106],"be":[78],"optimal.":[79],"work,":[82],"introduce":[84],"Adaptive":[85],"Maximum":[86],"Entropy":[87],"Regularization":[88],"(AdaMER),":[89],"technique":[91],"can":[93],"modulate":[94],"impact":[96],"throughout":[100],"training":[102,111,116],"process.":[103],"approach":[105],"only":[107],"refines":[108],"ASR":[109],"model":[110,122],"but":[112],"ensures":[113],"proceeds,":[117],"predictions":[118],"display":[119],"desired":[121],"confidence.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}