{"id":"https://openalex.org/W4372266908","doi":"https://doi.org/10.1109/icassp49357.2023.10095227","title":"Dynamic Alignment Mask CTC: Improved Mask CTC With Aligned Cross Entropy","display_name":"Dynamic Alignment Mask CTC: Improved Mask CTC With Aligned Cross Entropy","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266908","doi":"https://doi.org/10.1109/icassp49357.2023.10095227"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":"https://openalex.org/A5028437800","display_name":"Xulong Zhang","orcid":"https://orcid.org/0000-0001-7005-992X"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Xulong Zhang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055352265","display_name":"Haobin Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Tang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd","University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065576761","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0003-0909-5328"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608965","display_name":"Jianbin Luo","orcid":"https://orcid.org/0000-0002-5132-0712"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luo","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054879126","display_name":"Jing Jian Xiao","orcid":"https://orcid.org/0000-0003-3252-5672"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5028437800"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":0.5882,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69689774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7831094264984131},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.700713038444519},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6373387575149536},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5612500309944153},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.520248532295227},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5076926946640015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5012457370758057},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.49455663561820984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46191859245300293},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44127678871154785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40993595123291016},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3280419707298279},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11346670985221863},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10325050354003906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831094264984131},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.700713038444519},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6373387575149536},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5612500309944153},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.520248532295227},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5076926946640015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5012457370758057},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.49455663561820984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46191859245300293},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44127678871154785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40993595123291016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3280419707298279},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11346670985221863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10325050354003906},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2988975212","https://openalex.org/W3000840023","https://openalex.org/W3015162217","https://openalex.org/W3035445001","https://openalex.org/W3097625183","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3128442956","https://openalex.org/W3141854550","https://openalex.org/W3160622492","https://openalex.org/W3162431424","https://openalex.org/W3162899666","https://openalex.org/W3196321886","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6773383770","https://openalex.org/W6774835902","https://openalex.org/W6775291257","https://openalex.org/W6777996268","https://openalex.org/W6784188957","https://openalex.org/W6790624934","https://openalex.org/W6792376965"],"related_works":["https://openalex.org/W2355499516","https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W4380551034","https://openalex.org/W2033009170","https://openalex.org/W2110525351","https://openalex.org/W3015162217","https://openalex.org/W3034892578"],"abstract_inverted_index":{"Because":[0],"of":[1,17,98,133],"predicting":[2],"all":[3],"the":[4,9,14,43,48,72,95,100,125,130],"target":[5],"tokens":[6,85],"in":[7,87],"parallel,":[8],"non-autoregressive":[10],"models":[11],"greatly":[12],"improve":[13,129],"decoding":[15],"efficiency":[16],"speech":[18],"recognition":[19],"compared":[20],"with":[21,65],"traditional":[22],"autoregressive":[23],"models.":[24],"In":[25],"this":[26],"work,":[27],"we":[28],"present":[29],"dynamic":[30,52,91],"alignment":[31,45,75],"Mask":[32,134],"CTC,":[33],"introducing":[34],"two":[35],"methods:":[36],"(1)":[37],"Aligned":[38],"Cross":[39],"Entropy":[40],"(AXE),":[41],"finding":[42],"monotonic":[44],"that":[46,118],"minimizes":[47],"cross-entropy":[49],"loss":[50,122],"through":[51],"programming,":[53],"(2)":[54],"Dynamic":[55],"Rectification,":[56],"creating":[57],"new":[58],"training":[59],"samples":[60],"by":[61],"replacing":[62],"some":[63],"masks":[64],"model":[66,96],"predicted":[67],"tokens.":[68],"The":[69,90],"AXE":[70,121],"ignores":[71],"absolute":[73],"position":[74],"between":[76],"prediction":[77],"and":[78,82],"ground":[79],"truth":[80],"sentence":[81],"focuses":[83],"on":[84,114],"matching":[86],"relative":[88],"order.":[89],"rectification":[92,126],"method":[93,127],"makes":[94],"capable":[97],"simulating":[99],"non-mask":[101],"but":[102,123],"possible":[103],"wrong":[104],"tokens,":[105],"even":[106],"if":[107],"they":[108],"have":[109],"high":[110],"confidence.":[111],"Our":[112],"experiments":[113],"WSJ":[115],"dataset":[116],"demonstrated":[117],"not":[119],"only":[120],"also":[124],"could":[128],"WER":[131],"performance":[132],"CTC.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}