{"id":"https://openalex.org/W4389317789","doi":"https://doi.org/10.1109/taslp.2023.3337670","title":"Representation Learning With Hidden Unit Clustering for Low Resource Speech Applications","display_name":"Representation Learning With Hidden Unit Clustering for Low Resource Speech Applications","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4389317789","doi":"https://doi.org/10.1109/taslp.2023.3337670"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3337670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3337670","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":true,"raw_author_name":"Varun Krishna","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102708778","display_name":"Tarun Sai","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":"Tarun Sai","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India","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":["Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053022933"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58175601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"1036","last_page":"1047"},"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":0.9995999932289124,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6267570853233337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5857175588607788},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5614322423934937},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5582025647163391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5475971102714539},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47035670280456543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3631974756717682},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34078145027160645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1550513505935669},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.07138761878013611}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6267570853233337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5857175588607788},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5614322423934937},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5582025647163391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5475971102714539},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47035670280456543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3631974756717682},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34078145027160645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1550513505935669},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.07138761878013611},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/taslp.2023.3337670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3337670","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1973041621","https://openalex.org/W2029685080","https://openalex.org/W2030931454","https://openalex.org/W2097749765","https://openalex.org/W2107223151","https://openalex.org/W2114347655","https://openalex.org/W2124509324","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2295598076","https://openalex.org/W2394873997","https://openalex.org/W2395899413","https://openalex.org/W2726515241","https://openalex.org/W2741692265","https://openalex.org/W2752796333","https://openalex.org/W2756577849","https://openalex.org/W2766219058","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/W2889087444","https://openalex.org/W2896457183","https://openalex.org/W2963620343","https://openalex.org/W2972943112","https://openalex.org/W2972984069","https://openalex.org/W2973049979","https://openalex.org/W2995181338","https://openalex.org/W2996728628","https://openalex.org/W3006926732","https://openalex.org/W3011411500","https://openalex.org/W3015213852","https://openalex.org/W3035725276","https://openalex.org/W3041561163","https://openalex.org/W3093096176","https://openalex.org/W3095361818","https://openalex.org/W3097777922","https://openalex.org/W3100270690","https://openalex.org/W3163793923","https://openalex.org/W3197259906","https://openalex.org/W3197349023","https://openalex.org/W3197381195","https://openalex.org/W3198815374","https://openalex.org/W3209059054","https://openalex.org/W4224918488","https://openalex.org/W4239510810","https://openalex.org/W4297808394","https://openalex.org/W4385571911","https://openalex.org/W4385822567","https://openalex.org/W4385822823","https://openalex.org/W4394671563","https://openalex.org/W6636915900","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6790356757","https://openalex.org/W6810673746","https://openalex.org/W6996577779"],"related_works":["https://openalex.org/W611386996","https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2371343292","https://openalex.org/W2158836806","https://openalex.org/W2393816671"],"abstract_inverted_index":{"In":[0,180],"this":[1],"paper,":[2],"we":[3,183],"describe":[4],"an":[5,114],"approach":[6,141],"to":[7,23,88,201],"self-supervised":[8],"representation":[9,65],"learning":[10,93],"from":[11,43],"raw":[12],"audio":[13,28,107],"using":[14],"a":[15,62,80],"hidden":[16],"unit":[17],"clustering":[18],"(HUC)":[19],"framework.":[20],"The":[21,39,70,98],"input":[22],"the":[24,44,74,77,90,127,131,136,139,151,157,170,175,193,196],"model":[25,91],"consists":[26],"of":[27,76,83,101,130,138,156],"samples":[29],"that":[30,125],"are":[31,50,111,199],"windowed":[32,68],"and":[33,109,134,161,173,211],"processed":[34,52],"with":[35,53,113],"1-D":[36],"convolutional":[37,45],"layers.":[38],"learned":[40,132],"\u201ctime-frequency\u201d":[41],"representations":[42,78,133,198],"neural":[46],"network":[47],"(CNN)":[48],"module":[49],"further":[51],"long":[54],"short":[55],"term":[56],"memory":[57],"(LSTM)":[58],"layers":[59],"which":[60],"generate":[61],"contextual":[63],"vector":[64],"for":[66,92,105,187],"every":[67],"segment.":[69],"HUC":[71,197],"framework,":[72],"allowing":[73],"categorization":[75],"into":[79],"small":[81],"number":[82],"phoneme-like":[84,102],"units,":[85],"is":[86],"used":[87],"train":[89],"semantically":[94],"rich":[95],"speech":[96,148,165],"representations.":[97],"targets":[99],"consist":[100],"pseudo":[103],"labels":[104],"each":[106],"segment":[108],"these":[110,181],"generated":[112],"iterative":[115],"<inline-formula":[116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[118],"notation=\"LaTeX\">$k$</tex-math></inline-formula>":[119],"-means":[120],"algorithm.":[121],"We":[122],"explore":[123],"techniques":[124],"improve":[126,202],"speaker":[128],"invariance":[129],"illustrate":[135],"effectiveness":[137],"proposed":[140],"on":[142,150,169,174,192,208],"two":[143],"settings,":[144],"i)":[145],"completely":[146],"unsupervised":[147],"applications":[149,168],"sub-tasks":[152],"described":[153],"as":[154],"part":[155],"ZeroSpeech":[158],"2021":[159],"challenge":[160,177],"ii)":[162],"semi-supervised":[163],"automatic":[164],"recognition":[166],"(ASR)":[167],"TIMIT":[171],"dataset":[172],"GramVaani":[176],"Hindi":[178],"dataset.":[179],"experiments,":[182,195],"achieve":[184],"state-of-art":[185],"results":[186],"various":[188],"Zerospeech":[189],"tasks.":[190],"Further,":[191],"ASR":[194],"shown":[200],"over":[203],"other":[204],"established":[205],"benchmarks":[206],"based":[207],"wav2vec,":[209],"HuBERT":[210],"Best-RQ.":[212]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}