{"id":"https://openalex.org/W4402390174","doi":"https://doi.org/10.1109/icasspw62465.2024.10669906","title":"Exploring Dominant Paths in CTC-Like ASR Models: Unraveling the Effectiveness of Viterbi Decoding","display_name":"Exploring Dominant Paths in CTC-Like ASR Models: Unraveling the Effectiveness of Viterbi Decoding","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4402390174","doi":"https://doi.org/10.1109/icasspw62465.2024.10669906"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10669906","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10669906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5100775936","display_name":"Zeyu Zhao","orcid":"https://orcid.org/0009-0002-6612-9731"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zeyu Zhao","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Klejch","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12302982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"868","last_page":"872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9914000034332275,"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":0.9901999831199646,"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/computer-science","display_name":"Computer science","score":0.7444041967391968},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7126370072364807},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.6993430852890015},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6467382907867432},{"id":"https://openalex.org/keywords/soft-output-viterbi-algorithm","display_name":"Soft output Viterbi algorithm","score":0.569395124912262},{"id":"https://openalex.org/keywords/iterative-viterbi-decoding","display_name":"Iterative Viterbi decoding","score":0.4724048972129822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4042740762233734},{"id":"https://openalex.org/keywords/sequential-decoding","display_name":"Sequential decoding","score":0.38105762004852295},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17883235216140747}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444041967391968},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7126370072364807},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.6993430852890015},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6467382907867432},{"id":"https://openalex.org/C130319729","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Soft output Viterbi algorithm","level":5,"score":0.569395124912262},{"id":"https://openalex.org/C113638808","wikidata":"https://www.wikidata.org/wiki/Q6094410","display_name":"Iterative Viterbi decoding","level":5,"score":0.4724048972129822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4042740762233734},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.38105762004852295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17883235216140747},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10669906","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10669906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1710082047","https://openalex.org/W1895481600","https://openalex.org/W2122364000","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2132991150","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2520160253","https://openalex.org/W2748816379","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2953190524","https://openalex.org/W2963211739","https://openalex.org/W2990138404","https://openalex.org/W3016053754","https://openalex.org/W3097777922","https://openalex.org/W3205405669","https://openalex.org/W4205130185","https://openalex.org/W4224925075","https://openalex.org/W4281779489","https://openalex.org/W4287647128","https://openalex.org/W4319862408","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6727336983","https://openalex.org/W6766978945","https://openalex.org/W6780218876","https://openalex.org/W6838276489"],"related_works":["https://openalex.org/W2143297499","https://openalex.org/W3096277017","https://openalex.org/W1915619113","https://openalex.org/W2544568790","https://openalex.org/W2921374214","https://openalex.org/W3194244515","https://openalex.org/W2510070518","https://openalex.org/W176266968","https://openalex.org/W2165098971","https://openalex.org/W1843778016"],"abstract_inverted_index":{"Connectionist":[0],"Temporal":[1],"Classification":[2],"(CTC)":[3],"has":[4],"emerged":[5],"as":[6,81],"a":[7,57,77,133,141],"fundamental":[8],"technique":[9],"in":[10,47,61,90],"Automatic":[11],"Speech":[12],"Recognition":[13],"(ASR),":[14],"renowned":[15],"for":[16,44,107],"its":[17],"ability":[18],"to":[19,87,96,132],"marginalise":[20],"all":[21],"possible":[22],"alignments":[23,43],"between":[24],"input":[25],"and":[26],"target":[27],"sequences.":[28],"This":[29,93],"study":[30],"reevaluates":[31],"the":[32,54,62,68,74,82,91,113,117,123],"traditional":[33],"dependency":[34],"on":[35],"prefix":[36,78],"beam":[37,79],"search,":[38,80],"which":[39],"typically":[40],"considers":[41],"multiple":[42],"each":[45],"hypothesis,":[46],"CTC-based":[48],"models.":[49],"Our":[50],"findings":[51],"initially":[52],"indicate":[53],"absence":[55],"of":[56,76,125,135],"single":[58],"dominant":[59,89],"path":[60],"lattices.":[63,92],"However,":[64],"we":[65],"discover":[66],"that":[67,98],"Viterbi":[69,126],"decoder":[70],"can":[71],"effectively":[72],"emulate":[73],"performance":[75],"hypotheses":[83],"it":[84],"identifies":[85],"tend":[86],"be":[88],"leads":[94],"us":[95],"propose":[97],"an":[99],"effective":[100],"CTC-like":[101],"model":[102],"should":[103],"not":[104],"only":[105],"aim":[106],"high":[108],"accuracy":[109],"but":[110],"also":[111],"align":[112],"optimal":[114],"hypothesis":[115],"with":[116],"most":[118],"probable":[119],"path,":[120],"thereby":[121],"enhancing":[122],"robustness":[124],"decoding.":[127],"Furthermore,":[128],"our":[129],"insights":[130],"extend":[131],"variety":[134],"topologies,":[136],"demonstrating":[137],"their":[138],"applicability":[139],"within":[140],"more":[142],"comprehensive":[143],"ASR":[144],"framework.":[145]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}