{"id":"https://openalex.org/W7134843469","doi":"https://doi.org/10.1109/lsp.2026.3672001","title":"Alignment Regularization for Neural Transducer via Cross-Modal Optimal Transport","display_name":"Alignment Regularization for Neural Transducer via Cross-Modal Optimal Transport","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7134843469","doi":"https://doi.org/10.1109/lsp.2026.3672001"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3672001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3672001","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5128690126","display_name":"Ji-Hwan Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Ji-Hwan Mo","raw_affiliation_strings":["School of Electronic Engineering, Hanyang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128669816","display_name":"Dong-Hyun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Hyun Kim","raw_affiliation_strings":["School of Electronic Engineering, Hanyang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124150476","display_name":"Jae-Hong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I83436808","display_name":"Hankuk University of Foreign Studies","ror":"https://ror.org/051q2m369","country_code":"KR","type":"education","lineage":["https://openalex.org/I83436808"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Hong Lee","raw_affiliation_strings":["Division of Language &amp; AI, Hankuk University of Foreign Studies, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Division of Language &amp; AI, Hankuk University of Foreign Studies, Seoul, South Korea","institution_ids":["https://openalex.org/I83436808"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128658547","display_name":"Joon-Hyuk Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["School of Electronic Engineering, Hanyang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5128690126"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71019396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1285","last_page":"1289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.45890000462532043,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.45890000462532043,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10339999943971634,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.09049999713897705,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6518999934196472},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6467000246047974},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6377000212669373},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5924999713897705},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5622000098228455},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.47040000557899475},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4587000012397766},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4278999865055084},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.39559999108314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6786999702453613},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6518999934196472},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5015000104904175},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4278999865055084},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.26440000534057617},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2599000036716461},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3672001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3672001","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2746192915","https://openalex.org/W2789285779","https://openalex.org/W2911544293","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963827914","https://openalex.org/W3007227084","https://openalex.org/W3016010032","https://openalex.org/W3034368386","https://openalex.org/W3048407879","https://openalex.org/W3096518646","https://openalex.org/W3097777922","https://openalex.org/W3112157188","https://openalex.org/W3160628828","https://openalex.org/W3162649911","https://openalex.org/W3203453034","https://openalex.org/W4233762729","https://openalex.org/W4283700324","https://openalex.org/W4360930497","https://openalex.org/W4372270753","https://openalex.org/W4385822425","https://openalex.org/W4387987051","https://openalex.org/W4391021509","https://openalex.org/W4404035088"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"transducer":[1],"models":[2,50],"learn":[3],"alignments":[4,19],"implicitly":[5],"by":[6],"marginalizing":[7],"over":[8],"all":[9],"valid":[10],"paths,":[11],"which":[12,74],"can":[13],"lead":[14],"to":[15,40,92],"unstable":[16],"or":[17,51],"sub-optimal":[18],"under":[20],"low-resource":[21,147],"and":[22,36,78,85,102,119,130,149],"streaming":[23],"conditions":[24],"where":[25],"alignment":[26,66,81,105,128],"ambiguity":[27],"is":[28],"prevalent.":[29],"Previous":[30],"approaches":[31],"such":[32],"as":[33],"knowledge":[34],"distillation":[35],"pruned":[37],"transducers":[38],"attempt":[39],"mitigate":[41],"this,":[42],"but":[43],"they":[44],"either":[45],"rely":[46],"on":[47,70,115,139],"large":[48],"teacher":[49],"impose":[52],"rigid":[53],"pruning":[54],"strategies":[55],"that":[56,123],"limit":[57],"flexibility.":[58],"In":[59],"this":[60,91],"work,":[61],"we":[62],"propose":[63],"a":[64,76,93],"self-guided":[65],"regularization":[67],"framework":[68],"based":[69],"optimal":[71],"transport":[72],"(OT),":[73],"computes":[75],"soft":[77],"globally":[79],"consistent":[80],"plan":[82],"between":[83],"encoder":[84],"prediction":[86],"embeddings.":[87],"We":[88],"further":[89],"extend":[90],"dynamic":[94],"unbalanced":[95],"OT":[96],"formulation":[97],"with":[98],"relaxed":[99],"marginal":[100],"constraints":[101],"integrate":[103],"OT-derived":[104],"features":[106],"into":[107],"the":[108,116,146,152],"joint":[109],"network":[110],"via":[111],"residual":[112],"fusion.":[113],"Experiments":[114],"LibriSpeech":[117],"100h":[118],"960h":[120],"benchmarks":[121],"showed":[122],"our":[124],"method":[125],"consistently":[126],"improved":[127],"quality":[129],"recognition":[131],"accuracy,":[132],"yielding":[133],"relative":[134],"WER":[135],"reductions":[136],"of":[137],"14.45%/6.27%":[138],"<monospace":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141,143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">test-clean</monospace>/<monospace":[142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">test-other</monospace>":[144],"in":[145,151],"setting":[148],"25.49%/10.81%":[150],"high-resource":[153],"setting,":[154],"without":[155],"increasing":[156],"inference":[157],"complexity.":[158]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-11T00:00:00"}