{"id":"https://openalex.org/W3160913426","doi":"https://doi.org/10.1109/icassp39728.2021.9413645","title":"SEQ-CPC : Sequential Contrastive Predictive Coding for Automatic Speech Recognition","display_name":"SEQ-CPC : Sequential Contrastive Predictive Coding for Automatic Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160913426","doi":"https://doi.org/10.1109/icassp39728.2021.9413645","mag":"3160913426"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100777438","display_name":"Yulong Chen","orcid":"https://orcid.org/0000-0002-4960-5241"},"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":"Yulong Chen","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028520338","display_name":"Jianping Zhao","orcid":"https://orcid.org/0000-0003-0824-538X"},"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":"Jianping Zhao","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601726","display_name":"Weiqi Wang","orcid":"https://orcid.org/0000-0002-1617-9805"},"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":"Weiqi Wang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080919889","display_name":"Ming Fang","orcid":"https://orcid.org/0000-0003-1932-2037"},"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":"Ming Fang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063337275","display_name":"Haimei Kang","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"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Haimei Kang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364541","display_name":"Lu Wang","orcid":"https://orcid.org/0000-0003-4016-4096"},"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":"Lu Wang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049112187","display_name":"Tao Wei","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"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Wei","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029545637","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0002-7229-9756"},"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":"Jun Ma","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"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":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"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"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100777438"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67388786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3880","last_page":"3884"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.7752326726913452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6868817806243896},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5392263531684875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383585095405579},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5354101657867432},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4418213963508606},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.43942901492118835},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4303942322731018},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41449400782585144},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41027188301086426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09233108162879944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752326726913452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6868817806243896},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5392263531684875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383585095405579},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5354101657867432},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4418213963508606},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.43942901492118835},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4303942322731018},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41449400782585144},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41027188301086426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09233108162879944},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/icassp39728.2021.9413645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":56,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W2122028591","https://openalex.org/W2152790380","https://openalex.org/W2193413348","https://openalex.org/W2326925005","https://openalex.org/W2478708596","https://openalex.org/W2842511635","https://openalex.org/W2887997457","https://openalex.org/W2896457183","https://openalex.org/W2900898015","https://openalex.org/W2930682606","https://openalex.org/W2944828972","https://openalex.org/W2946006146","https://openalex.org/W2949759968","https://openalex.org/W2955425717","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2972894903","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2994658979","https://openalex.org/W2995406823","https://openalex.org/W2996383576","https://openalex.org/W2996428491","https://openalex.org/W3015486994","https://openalex.org/W3022824298","https://openalex.org/W3034541796","https://openalex.org/W3035058308","https://openalex.org/W3037428746","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W4289294839","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6682948231","https://openalex.org/W6687566353","https://openalex.org/W6739901393","https://openalex.org/W6754278344","https://openalex.org/W6755207826","https://openalex.org/W6755987414","https://openalex.org/W6756331379","https://openalex.org/W6761553608","https://openalex.org/W6762718338","https://openalex.org/W6762796984","https://openalex.org/W6768021236","https://openalex.org/W6768890659","https://openalex.org/W6769196770","https://openalex.org/W6771213955","https://openalex.org/W6775675442"],"related_works":["https://openalex.org/W2466816617","https://openalex.org/W1970834875","https://openalex.org/W842936808","https://openalex.org/W3174028392","https://openalex.org/W2000517284","https://openalex.org/W2365318811","https://openalex.org/W2136503713","https://openalex.org/W2375330620","https://openalex.org/W2363755581","https://openalex.org/W2067317451"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"the":[2,28,50,60,66,97,106],"contrastive":[3,107],"predictive":[4],"coding":[5],"(CPC),":[6],"we":[7,58],"propose":[8],"a":[9,32],"feature":[10],"representation":[11],"scheme":[12],"for":[13,31],"automatic":[14],"speech":[15,74],"recognition":[16,86],"(ASR),":[17],"which":[18,64,104],"encodes":[19],"sequential":[20,61,67,81],"dependency":[21],"information":[22,36,68,82],"from":[23],"raw":[24],"audio":[25],"signals.":[26],"Following":[27],"original":[29,56],"CPC,":[30,57],"given":[33],"frame,":[34],"mutual":[35],"(MI)":[37],"lower":[38,52],"bound":[39],"is":[40,105],"maximized":[41],"between":[42,69],"historical":[43],"context":[44],"and":[45,102],"future":[46],"prediction.":[47],"While":[48],"computing":[49],"MI":[51],"bound,":[53],"based":[54],"on":[55,90],"develop":[59],"CPC":[62,101],"(SEQ-CPC),":[63],"takes":[65],"frames":[70,75],"into":[71],"consideration.":[72],"Since":[73],"are":[76],"not":[77],"independent":[78],"events,":[79],"incorporating":[80],"leads":[83],"to":[84],"better":[85],"performance.":[87],"Experimental":[88],"results":[89],"WSJ":[91],"corpus":[92],"show":[93],"that":[94],"SEQ-CPC":[95],"achieves":[96],"best":[98],"performance":[99],"than":[100],"NCE":[103],"objective":[108],"used":[109],"in":[110],"wav2vec.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}