{"id":"https://openalex.org/W4392903518","doi":"https://doi.org/10.1109/icassp48485.2024.10447530","title":"Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling","display_name":"Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903518","doi":"https://doi.org/10.1109/icassp48485.2024.10447530"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447530","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":null,"display_name":"Zheng Nan","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zheng Nan","raw_affiliation_strings":["University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","School of Electrical Engineering and Telecommunications, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071116593","display_name":"Ting Dang","orcid":"https://orcid.org/0000-0003-3806-1493"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"Ting Dang","raw_affiliation_strings":["University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","Department of Computer Science and Technology, University of Cambridge, Cambridge, UK","Nokia Bell Labs, UK","School of Electrical Engineering and Telecommunications, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Nokia Bell Labs, UK","institution_ids":["https://openalex.org/I4210098141"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032689109","display_name":"Vidhyasaharan Sethu","orcid":"https://orcid.org/0000-0001-8492-1787"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vidhyasaharan Sethu","raw_affiliation_strings":["University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","School of Electrical Engineering and Telecommunications, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077436139","display_name":"Beena Ahmed","orcid":"https://orcid.org/0000-0002-1240-6572"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Beena Ahmed","raw_affiliation_strings":["University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","School of Electrical Engineering and Telecommunications, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2219,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81453731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6495","last_page":"6499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.8316822648048401},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7399158477783203},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6856119632720947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6102604269981384},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5107345581054688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47921663522720337},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47521883249282837},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4438812732696533},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42003333568573},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3485739231109619},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32550567388534546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3095683157444}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.8316822648048401},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7399158477783203},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6856119632720947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6102604269981384},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5107345581054688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47921663522720337},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47521883249282837},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4438812732696533},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42003333568573},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3485739231109619},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32550567388534546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3095683157444},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447530","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":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2105482032","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2962974924","https://openalex.org/W2963039488","https://openalex.org/W3015315932","https://openalex.org/W3089611792","https://openalex.org/W3096966883","https://openalex.org/W3203412535","https://openalex.org/W3211278025","https://openalex.org/W4212774754","https://openalex.org/W4235646468","https://openalex.org/W4392902746","https://openalex.org/W6617744952","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6640963894","https://openalex.org/W6687045409","https://openalex.org/W6746923139","https://openalex.org/W6751433836","https://openalex.org/W6779961481","https://openalex.org/W6780218876","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263","https://openalex.org/W2504816413"],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1],"classification":[2],"(CTC)":[3],"is":[4,16,29,40],"commonly":[5],"adopted":[6],"for":[7,141,150],"sequence":[8,34,82],"modeling":[9],"tasks":[10],"like":[11],"speech":[12],"recognition,":[13],"where":[14,36],"it":[15],"necessary":[17],"to":[18,32,57,78],"preserve":[19,85],"order":[20],"between":[21],"the":[22,37,93,102,106,118,137,142],"input":[23],"and":[24,42,70,117,145],"target":[25],"sequences.":[26],"However,":[27],"CTC":[28,65,96],"only":[30],"applied":[31],"deterministic":[33],"models,":[35],"latent":[38,108,123],"space":[39],"discontinuous":[41],"sparse,":[43],"which":[44],"in":[45],"turn":[46],"makes":[47],"them":[48],"less":[49],"capable":[50],"of":[51,92,136],"handling":[52],"data":[53],"variability":[54],"when":[55],"compared":[56],"variational":[58,68,95,107,138],"models.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,88],"integrate":[64],"with":[66],"a":[67],"model":[69,143],"derive":[71,89],"loss":[72,131],"functions":[73,132],"that":[74,84,105,121,129],"can":[75],"be":[76],"used":[77],"train":[79],"more":[80],"generalizable":[81],"models":[83],"order.":[86],"Specifically,":[87],"two":[90,99],"versions":[91],"novel":[94],"based":[97],"on":[98],"reasonable":[100],"assumptions,":[101],"first":[103],"being":[104,120],"variables":[109,124],"at":[110],"each":[111],"time":[112],"step":[113],"are":[114,125],"conditionally":[115],"independent;":[116],"second":[119],"these":[122],"Markovian.":[126],"We":[127],"show":[128],"both":[130],"allow":[133],"direct":[134],"optimization":[135],"lower":[139],"bound":[140],"log-likelihood,":[144],"present":[146],"computationally":[147],"tractable":[148],"forms":[149],"implementing":[151],"them.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
