{"id":"https://openalex.org/W4224918488","doi":"https://doi.org/10.1109/icassp43922.2022.9747259","title":"Self Supervised Representation Learning with Deep Clustering for Acoustic Unit Discovery from Raw Speech","display_name":"Self Supervised Representation Learning with Deep Clustering for Acoustic Unit Discovery from Raw Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918488","doi":"https://doi.org/10.1109/icassp43922.2022.9747259"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747259","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5053022933","display_name":"Varun Krishna","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Varun Krishna","raw_affiliation_strings":["Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2076,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37911476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"3268","last_page":"3272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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":0.776543378829956},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6881060600280762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.612364649772644},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5507265329360962},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4627983272075653},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43567103147506714},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43333524465560913},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41326117515563965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37900054454803467},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3394402861595154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776543378829956},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6881060600280762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.612364649772644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5507265329360962},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4627983272075653},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43567103147506714},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43333524465560913},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41326117515563965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37900054454803467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3394402861595154},{"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":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747259","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai::73938","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1949782964","https://openalex.org/W1957665339","https://openalex.org/W2114347655","https://openalex.org/W2117041980","https://openalex.org/W2124509324","https://openalex.org/W2187089797","https://openalex.org/W2741692265","https://openalex.org/W2752796333","https://openalex.org/W2785860501","https://openalex.org/W2786608204","https://openalex.org/W2787223168","https://openalex.org/W2787447541","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2896457183","https://openalex.org/W2935542736","https://openalex.org/W2963620343","https://openalex.org/W2963799213","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2995181338","https://openalex.org/W2996728628","https://openalex.org/W3015213852","https://openalex.org/W3035725276","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3093096176","https://openalex.org/W3095361818","https://openalex.org/W3096216486","https://openalex.org/W3100270690","https://openalex.org/W3197259906","https://openalex.org/W3197381195","https://openalex.org/W4297808394","https://openalex.org/W4394671563","https://openalex.org/W6629717138","https://openalex.org/W6640828828","https://openalex.org/W6753000030","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6770941677","https://openalex.org/W6771812881","https://openalex.org/W6780218876","https://openalex.org/W6790356757"],"related_works":["https://openalex.org/W8787759","https://openalex.org/W2308727","https://openalex.org/W11114093","https://openalex.org/W9770290","https://openalex.org/W4178615","https://openalex.org/W13343246","https://openalex.org/W14719770","https://openalex.org/W2786391","https://openalex.org/W5470487","https://openalex.org/W505292"],"abstract_inverted_index":{"The":[0,21,91,108],"automatic":[1,126],"discovery":[2],"of":[3,19,28,38,52,110,125,137,146,173,178],"acoustic":[4],"sub-word":[5],"units":[6,40],"from":[7],"raw":[8],"speech,":[9],"without":[10],"any":[11],"text":[12],"or":[13],"labels,":[14],"is":[15,24],"a":[16,35,59,122,176],"growing":[17],"field":[18],"research.":[20],"key":[22],"challenge":[23,141],"to":[25,142],"derive":[26],"representations":[27,117],"speech":[29,127],"that":[30,64,114,154],"can":[31,46,118],"be":[32,119],"categorized":[33,120],"into":[34,121],"small":[36,123],"number":[37,124],"phoneme-like":[39,100],"which":[41],"are":[42,89],"speaker":[43],"invariant":[44],"and":[45,85,182],"broadly":[47],"capture":[48],"the":[49,66,72,80,83,86,95,99,115,138,144,147,162,170],"content":[50],"variability":[51],"speech.":[53],"In":[54,149],"this":[55,111],"work,":[56],"we":[57,152],"propose":[58],"novel":[60],"neural":[61],"network":[62],"paradigm":[63],"uses":[65],"deep":[67],"clustering":[68,87,92],"loss":[69,81,96,112],"along":[70],"with":[71,103,131],"autoregressive":[73],"contrastive":[74],"predictive":[75],"coding":[76],"(CPC)":[77],"loss.":[78],"Both":[79],"functions,":[82],"CPC":[84],"loss,":[88],"self-supervised.":[90],"cost":[93],"involves":[94],"function":[97],"using":[98],"labels":[101],"generated":[102],"an":[104],"iterative":[105],"k-means":[106],"algorithm.":[107],"inclusion":[109],"ensures":[113],"model":[116],"units.":[128],"We":[129],"experiment":[130],"several":[132],"sub-tasks":[133],"described":[134],"as":[135,167,169],"part":[136],"Zerospeech":[139],"2021":[140],"illustrate":[143],"effectiveness":[145],"framework.":[148],"these":[150],"experiments,":[151],"show":[153],"proposed":[155],"representation":[156],"learning":[157],"approach":[158],"improves":[159],"significantly":[160],"over":[161],"previous":[163],"self-supervision":[164],"based":[165],"models":[166,174],"well":[168],"wav2vec":[171],"family":[172],"on":[175],"range":[177],"word-level":[179],"similarity":[180],"tasks":[181],"language":[183],"modeling":[184],"tasks.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}