{"id":"https://openalex.org/W4319862416","doi":"https://doi.org/10.1109/slt54892.2023.10022552","title":"CCC-WAV2VEC 2.0: Clustering AIDED Cross Contrastive Self-Supervised Learning of Speech Representations","display_name":"CCC-WAV2VEC 2.0: Clustering AIDED Cross Contrastive Self-Supervised Learning of Speech Representations","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862416","doi":"https://doi.org/10.1109/slt54892.2023.10022552"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022552","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022552","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5075877984","display_name":"Vasista Sai Lodagala","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vasista Sai Lodagala","raw_affiliation_strings":["Indian Institute of Technology,Madras","Indian Institute of Technology, Madras"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033408639","display_name":"Sreyan Ghosh","orcid":"https://orcid.org/0000-0003-3773-561X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["University of Maryland,College Park","University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["Indian Institute of Technology,Madras","Indian Institute of Technology, Madras"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6135,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9144626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9987000226974487,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7252503037452698},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7236883640289307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.660108208656311},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6594599485397339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5598357915878296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.540108859539032},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5025098323822021},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4961749017238617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3696712255477905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36521100997924805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3402864933013916}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7252503037452698},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7236883640289307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.660108208656311},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6594599485397339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598357915878296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.540108859539032},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5025098323822021},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4961749017238617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3696712255477905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36521100997924805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3402864933013916},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022552","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022552","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2096733369","https://openalex.org/W2166637769","https://openalex.org/W2193413348","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2948638722","https://openalex.org/W2982223350","https://openalex.org/W3005680577","https://openalex.org/W3024869864","https://openalex.org/W3036224891","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3087124270","https://openalex.org/W3094225009","https://openalex.org/W3102363610","https://openalex.org/W3144810982","https://openalex.org/W3154677174","https://openalex.org/W3163839574","https://openalex.org/W3187822143","https://openalex.org/W3196843354","https://openalex.org/W3197580070","https://openalex.org/W3198608154","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221163898","https://openalex.org/W4226033575","https://openalex.org/W4283659485","https://openalex.org/W4297808394","https://openalex.org/W4297841844","https://openalex.org/W4301372783","https://openalex.org/W4306672449","https://openalex.org/W4318148707","https://openalex.org/W6687566353","https://openalex.org/W6688816777","https://openalex.org/W6713762819","https://openalex.org/W6774314701","https://openalex.org/W6779997284","https://openalex.org/W6780191644","https://openalex.org/W6780218876","https://openalex.org/W6783990618","https://openalex.org/W6798952882","https://openalex.org/W6809251386","https://openalex.org/W6839738141"],"related_works":["https://openalex.org/W4320472933","https://openalex.org/W4312741812","https://openalex.org/W4288350321","https://openalex.org/W3194633786","https://openalex.org/W2945374320","https://openalex.org/W2996325578","https://openalex.org/W105527591","https://openalex.org/W3094805729","https://openalex.org/W2949412037","https://openalex.org/W3035729345"],"abstract_inverted_index":{"While":[0],"Self-Supervised":[1],"Learning":[2],"has":[3],"helped":[4],"reap":[5],"the":[6,9,12,16,46,52,63,71,75,79,90,104,109,118,135],"benefit":[7],"of":[8,54,74,82,115,120],"scale":[10,50],"from":[11],"available":[13],"unlabeled":[14],"data,":[15],"learning":[17],"paradigms":[18],"are":[19,59],"continously":[20],"being":[21],"bettered.":[22],"We":[23],"present":[24],"a":[25],"new":[26],"pre-training":[27,91],"strategy":[28],"named":[29],"ccc-wav2vec":[30,93],"2.0,":[31,138],"which":[32],"uses":[33],"clustering":[34,47],"and":[35,78,85,98,111],"an":[36],"augmentation":[37],"based":[38],"cross-contrastive":[39],"loss":[40,67],"as":[41],"its":[42,83],"self-supervised":[43],"objective.":[44],"Through":[45],"module":[48],"we":[49],"down":[51],"influence":[53],"those":[55],"negative":[56],"examples":[57],"that":[58],"highly":[60],"similar":[61],"to":[62,89],"positive.":[64],"The":[65,124],"Cross-Contrastive":[66],"is":[68],"computed":[69],"between":[70],"encoder":[72],"output":[73,81],"original":[76],"sample":[77],"quantizer":[80],"augmentation,":[84],"vice-versa,":[86],"bringing":[87],"robustness":[88],"strategy.":[92],"2.0":[94,107],"achieves":[95,128],"upto":[96,129],"15.6%":[97],"12.7%":[99],"relative":[100,131],"WER":[101,132],"improvement":[102,133],"over":[103,134],"baseline":[105,136],"wav2vec":[106,137],"on":[108,141],"test-clean":[110],"test-other":[112],"sets":[113],"respectively":[114],"LibriSpeech,":[116],"without":[117],"use":[119],"any":[121],"language":[122],"model.":[123],"proposed":[125],"method":[126],"also":[127],"14.9%":[130],"when":[139],"fine-tuned":[140],"Switchboard":[142],"data.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}