{"id":"https://openalex.org/W3160399536","doi":"https://doi.org/10.1109/icassp39728.2021.9414352","title":"Contrastive Separative Coding for Self-Supervised Representation Learning","display_name":"Contrastive Separative Coding for Self-Supervised Representation Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160399536","doi":"https://doi.org/10.1109/icassp39728.2021.9414352","mag":"3160399536"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414352","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/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102313170","display_name":"Max W. Y. Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Max W Y. Lam","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2799,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62474503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"485","issue":null,"first_page":"3865","last_page":"3869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9984999895095825,"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":0.7929562330245972},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6432977914810181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5998960733413696},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5713625550270081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.540996789932251},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.537116289138794},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5222856998443604},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48404306173324585},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45536723732948303},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44774845242500305},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.433349072933197},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4303932785987854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38274893164634705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35554128885269165},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1651265025138855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929562330245972},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6432977914810181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5998960733413696},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5713625550270081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.540996789932251},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.537116289138794},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5222856998443604},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48404306173324585},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45536723732948303},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44774845242500305},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.433349072933197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4303932785987854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38274893164634705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35554128885269165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1651265025138855},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414352","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":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1494198834","https://openalex.org/W1614298861","https://openalex.org/W2046516274","https://openalex.org/W2082183045","https://openalex.org/W2119885245","https://openalex.org/W2127958135","https://openalex.org/W2153579005","https://openalex.org/W2158904676","https://openalex.org/W2221409856","https://openalex.org/W2268529521","https://openalex.org/W2326925005","https://openalex.org/W2460742184","https://openalex.org/W2760103357","https://openalex.org/W2794753807","https://openalex.org/W2842511635","https://openalex.org/W2887997457","https://openalex.org/W2889256969","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2950577311","https://openalex.org/W2962918106","https://openalex.org/W2963223524","https://openalex.org/W2963341956","https://openalex.org/W2963425185","https://openalex.org/W2963877604","https://openalex.org/W2964052309","https://openalex.org/W2964058413","https://openalex.org/W2964089206","https://openalex.org/W2972949456","https://openalex.org/W2972986505","https://openalex.org/W2973049979","https://openalex.org/W3008357631","https://openalex.org/W3015199127","https://openalex.org/W3016031604","https://openalex.org/W3027008958","https://openalex.org/W3095212884","https://openalex.org/W3119059628","https://openalex.org/W3146854175","https://openalex.org/W4297749157","https://openalex.org/W4297808394","https://openalex.org/W6636510571","https://openalex.org/W6701655646","https://openalex.org/W6740674931","https://openalex.org/W6748270630","https://openalex.org/W6754278344","https://openalex.org/W6755207826","https://openalex.org/W6768815455","https://openalex.org/W6777776875","https://openalex.org/W6788489116","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W4205463238","https://openalex.org/W2221419418","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W2619127353"],"abstract_inverted_index":{"To":[0],"extract":[1,48],"robust":[2],"deep":[3],"representations":[4,30,64,116,166],"from":[5,36,154],"long":[6],"sequential":[7],"modeling":[8],"of":[9,142],"speech":[10],"data,":[11],"we":[12,55,100,137],"propose":[13,56],"a":[14,41,57,102,139,168],"self-supervised":[15],"learning":[16],"approach,":[17],"namely":[18],"Contrastive":[19],"Separative":[20],"Coding":[21],"(CSC).":[22],"Our":[23],"key":[24],"finding":[25],"is":[26,45,152],"to":[27,47,72,82,93],"learn":[28,164],"such":[29],"by":[31],"separating":[32],"the":[33,70,78,84,111,115,118,131,144],"target":[34],"signal":[35],"contrastive":[37,105,149],"interfering":[38,67],"signals.":[39],"First,":[40],"multi-task":[42],"separative":[43,150],"encoder":[44],"built":[46],"shared":[49],"separable":[50],"and":[51,75,109,117],"discriminative":[52],"embedding;":[53],"secondly,":[54],"powerful":[58],"cross-attention":[59],"mechanism":[60],"performed":[61],"over":[62],"speaker":[63,120,170],"across":[65],"various":[66],"conditions,":[68],"allowing":[69],"model":[71],"focus":[73],"on":[74,129],"globally":[76],"aggregate":[77],"most":[79,123],"critical":[80],"information":[81,113],"answer":[83],"\"query\"":[85],"(current":[86],"bottom-up":[87],"embedding)":[88],"while":[89],"paying":[90],"less":[91],"attention":[92],"interfering,":[94],"noisy,":[95],"or":[96,134],"irrelevant":[97],"parts;":[98],"lastly,":[99],"form":[101],"new":[103],"probabilistic":[104],"loss":[106,151],"which":[107],"estimates":[108],"maximizes":[110],"mutual":[112],"between":[114],"global":[119],"vector.":[121],"While":[122],"prior":[124],"unsupervised":[125],"methods":[126],"have":[127],"focused":[128],"predicting":[130,143],"future,":[132],"neighboring,":[133],"missing":[135],"samples,":[136],"take":[138],"different":[140],"perspective":[141],"interfered":[145],"samples.":[146],"Moreover,":[147],"our":[148,161],"free":[153],"negative":[155],"sampling.":[156],"The":[157],"experiment":[158],"demonstrates":[159],"that":[160],"approach":[162],"can":[163],"useful":[165],"achieving":[167],"strong":[169],"verification":[171],"performance":[172],"in":[173],"adverse":[174],"conditions.":[175]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}