{"id":"https://openalex.org/W4415524006","doi":"https://doi.org/10.1109/mlsp62443.2025.11204240","title":"Diffusion-Based Connectionist Temporal Classification","display_name":"Diffusion-Based Connectionist Temporal Classification","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524006","doi":"https://doi.org/10.1109/mlsp62443.2025.11204240"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112509568","display_name":"Chia-Kai Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Kai Yeh","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061908942"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":1.6666,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89214942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13748","display_name":"Advanced Statistical Modeling Techniques","score":0.032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13748","display_name":"Advanced Statistical Modeling Techniques","score":0.032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11883","display_name":"Embodied and Extended Cognition","score":0.026799999177455902,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.02250000089406967,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7663999795913696},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.60589998960495},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5910000205039978},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5551999807357788},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.517300009727478},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5163000226020813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48240000009536743},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4300999939441681}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7663999795913696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905999779701233},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.60589998960495},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4903999865055084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4424999952316284},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1980516134","https://openalex.org/W2015631279","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2405331948","https://openalex.org/W2964411643","https://openalex.org/W3198347216","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210660489","https://openalex.org/W4225302952","https://openalex.org/W4392903108","https://openalex.org/W4392904348","https://openalex.org/W4399345616","https://openalex.org/W4402111238","https://openalex.org/W4402111999","https://openalex.org/W4408345880","https://openalex.org/W4408354606","https://openalex.org/W4408355767"],"related_works":[],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1,91],"classification":[2],"(CTC)":[3],"is":[4],"one":[5],"of":[6,15,30],"the":[7,31,34,76,105,119],"predominant":[8],"schemes":[9],"for":[10],"end-to-end":[11],"speech":[12],"recognition":[13],"because":[14],"its":[16,38],"simplicity,":[17],"efficiency":[18],"and":[19,51,114,125],"reliability.":[20],"However,":[21],"as":[22,46,80],"a":[23,57,65,81,97],"sequence":[24,82],"model,":[25],"CTC":[26,60,87,127],"assumes":[27],"conditional":[28],"independence":[29],"outputs":[32],"given":[33],"inputs":[35],"which":[36,63,84],"limits":[37],"representation":[39],"capability":[40],"relative":[41],"to":[42,70,89,102],"other":[43],"methods":[44],"such":[45],"recurrent":[47],"neural":[48],"network":[49],"transducers":[50],"attention-based":[52],"encoder-decoders.":[53],"This":[54],"paper":[55],"presents":[56],"new":[58],"diffusion-based":[59],"model":[61,78],"(DiffCTC),":[62],"incorporates":[64],"discrete":[66],"absorbing":[67],"diffusion":[68,77,106],"component":[69],"mitigate":[71],"this":[72],"limitation.":[73],"In":[74,93],"DiffCTC,":[75],"functions":[79],"decoder":[83],"iteratively":[85],"refines":[86],"alignments":[88],"capture":[90],"dependencies.":[92],"particular,":[94],"we":[95],"propose":[96],"novel":[98],"dynamic":[99],"programming":[100],"algorithm":[101],"efficiently":[103],"compute":[104],"objective":[107],"during":[108],"training.":[109],"Experimental":[110],"results":[111],"on":[112],"LibriSpeech":[113],"Common":[115],"Voice":[116],"show":[117],"that":[118],"proposed":[120],"DiffCTC":[121],"captures":[122],"time":[123],"dependencies":[124],"surpasses":[126],"with":[128],"various":[129],"acoustic":[130],"encoders.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}