{"id":"https://openalex.org/W3198608154","doi":"https://doi.org/10.21437/interspeech.2021-391","title":"Speech SimCLR: Combining Contrastive and Reconstruction Objective for Self-Supervised Speech Representation Learning","display_name":"Speech SimCLR: Combining Contrastive and Reconstruction Objective for Self-Supervised Speech Representation Learning","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198608154","doi":"https://doi.org/10.21437/interspeech.2021-391","mag":"3198608154"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-391","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5110582135","display_name":"Dongwei Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongwei Jiang","raw_affiliation_strings":["AI Labs, YuanFuDao, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Labs, YuanFuDao, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050050390","display_name":"Wubo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wubo Li","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010070743","display_name":"Miao Cao","orcid":"https://orcid.org/0000-0001-7254-5227"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Cao","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108286207","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4215-5361"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1544","last_page":"1548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894999861717224,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894999861717224,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.972599983215332,"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":0.7837813496589661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6644078493118286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5433611869812012},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46823567152023315},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39850130677223206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837813496589661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6644078493118286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5433611869812012},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46823567152023315},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39850130677223206},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-391","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1568716973","https://openalex.org/W2146334809","https://openalex.org/W2219249508","https://openalex.org/W2251321385","https://openalex.org/W2404126548","https://openalex.org/W2936451900","https://openalex.org/W2936774411","https://openalex.org/W2944828972","https://openalex.org/W2963127222","https://openalex.org/W2964227577","https://openalex.org/W2972818416","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2988736778","https://openalex.org/W2995181338","https://openalex.org/W3005680577","https://openalex.org/W3015265920","https://openalex.org/W3016011332","https://openalex.org/W3034774681","https://openalex.org/W3035202887","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3046125265","https://openalex.org/W3102342027","https://openalex.org/W3144810982","https://openalex.org/W3148040514","https://openalex.org/W3160345865","https://openalex.org/W4214784181","https://openalex.org/W4385245566","https://openalex.org/W4398958419"],"related_works":["https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W1569841287","https://openalex.org/W1512718085","https://openalex.org/W2359001871","https://openalex.org/W2167662847","https://openalex.org/W1560657467"],"abstract_inverted_index":{"Self-supervised":[0],"visual":[1,31],"pretraining":[2],"has":[3],"shown":[4],"significant":[5],"progress":[6],"recently.Among":[7],"those":[8],"methods,":[9],"SimCLR":[10,65],"greatly":[11],"advanced":[12],"the":[13,16,76,89],"state":[14],"of":[15,78,95],"art":[17],"in":[18,88],"self-supervised":[19,57],"and":[20,30,71,92,107],"semisupervised":[21],"learning":[22],"on":[23,45,68,103],"ImageNet.The":[24],"input":[25,96],"feature":[26],"representations":[27],"for":[28,59],"speech":[29,46,60,70,104,108],"tasks":[32],"are":[33],"both":[34],"continuous,":[35],"so":[36],"it":[37],"is":[38,75],"natural":[39],"to":[40],"consider":[41],"applying":[42],"similar":[43],"objective":[44,58,74],"representation":[47,61],"learning.In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"Speech":[53,64],"SimCLR,":[54],"a":[55],"new":[56],"learning.During":[62],"training,":[63],"applies":[66],"augmentation":[67],"raw":[69],"its":[72],"spectrogram.Its":[73],"combination":[77],"contrastive":[79],"loss":[80,94],"that":[81],"maximizes":[82],"agreement":[83],"between":[84],"differently":[85],"augmented":[86],"samples":[87],"latent":[90],"space":[91],"reconstruction":[93],"representation.The":[97],"proposed":[98],"method":[99],"achieved":[100],"competitive":[101],"results":[102],"emotion":[105],"recognition":[106],"recognition.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}