{"id":"https://openalex.org/W4392910797","doi":"https://doi.org/10.1109/icassp48485.2024.10448248","title":"Unimodal Aggregation for CTC-Based Speech Recognition","display_name":"Unimodal Aggregation for CTC-Based Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910797","doi":"https://doi.org/10.1109/icassp48485.2024.10448248"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448248","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":"conference-paper","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/A5119309726","display_name":"Ying Fang","orcid":"https://orcid.org/0009-0003-8767-1172"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Fang","raw_affiliation_strings":["Zhejiang University,China","Zhejiang University, China","School of Engineering, Westlake University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Engineering, Westlake University, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358313","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["Westlake University,School of Engineering,China","School of Engineering, Westlake University, China","Institute of Advanced Technology, Westlake Institute for Advanced Study, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University,School of Engineering,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"School of Engineering, Westlake University, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Institute of Advanced Technology, Westlake Institute for Advanced Study, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10591","last_page":"10595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9879000186920166,"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":0.9879000186920166,"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":0.9444000124931335,"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":0.6659604907035828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.640224277973175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659604907035828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.640224277973175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448248","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":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1526236009","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W2889048668","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W3016167541","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3162249256","https://openalex.org/W3164692279","https://openalex.org/W3197140813","https://openalex.org/W3206573929","https://openalex.org/W4221151577","https://openalex.org/W4283067311","https://openalex.org/W4319862255","https://openalex.org/W4385823140","https://openalex.org/W6675365184","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"paper":[1],"works":[2],"on":[3,99],"non-autoregressive":[4,114],"automatic":[5],"speech":[6],"recognition.":[7],"A":[8],"unimodal":[9,54],"aggregation":[10],"(UMA)":[11],"is":[12,69],"proposed":[13,79,127],"to":[14,23,30,74,111],"segment":[15],"and":[16,28,41,58,85,95],"integrate":[17],"the":[18,24,50,75,78,87,126,129],"feature":[19,33,51,83],"frames":[20,52],"that":[21,104],"belong":[22],"same":[25],"text":[26,36],"token,":[27],"thus":[29],"learn":[31],"better":[32,82],"representations":[34,84],"for":[35,71],"tokens.":[37],"The":[38],"frame-wise":[39],"features":[40],"weights":[42,55],"are":[43,56],"both":[44],"derived":[45],"from":[46],"an":[47],"encoder.":[48],"Then,":[49],"with":[53],"integrated":[57],"further":[59,133],"processed":[60],"by":[61,121],"a":[62],"decoder.":[63],"Connectionist":[64],"temporal":[65],"classification":[66],"(CTC)":[67],"loss":[68],"applied":[70],"training.":[72],"Compared":[73],"regular":[76],"CTC,":[77],"method":[80],"learns":[81],"shortens":[86],"sequence":[88],"length,":[89],"resulting":[90],"in":[91],"lower":[92],"recognition":[93],"error":[94],"computational":[96],"complexity.":[97],"Experiments":[98],"three":[100],"Mandarin":[101],"datasets":[102],"show":[103],"UMA":[105],"demonstrates":[106],"superior":[107],"or":[108],"comparable":[109],"performance":[110,130],"other":[112],"advanced":[113],"methods,":[115],"such":[116],"as":[117],"self-conditioned":[118,123],"CTC.":[119],"Moreover,":[120],"integrating":[122],"CTC":[124],"into":[125],"framework,":[128],"can":[131],"be":[132],"noticeably":[134],"improved.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}