{"id":"https://openalex.org/W4406461625","doi":"https://doi.org/10.1109/slt61566.2024.10832198","title":"Estimating the Completeness of Discrete Speech Units","display_name":"Estimating the Completeness of Discrete Speech Units","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461625","doi":"https://doi.org/10.1109/slt61566.2024.10832198"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5016912114","display_name":"Sung-Lin Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sung-Lin Yeh","raw_affiliation_strings":["University of Edinburgh,School of Informatics"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["University of Edinburgh,School of Informatics"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016912114"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77766899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"415","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.9902999997138977,"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":0.6947805285453796},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.6394416689872742},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3880370259284973},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21335634589195251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947805285453796},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.6394416689872742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3880370259284973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21335634589195251},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1700083040","https://openalex.org/W1980280616","https://openalex.org/W2024490156","https://openalex.org/W2118774185","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2726515241","https://openalex.org/W2842511635","https://openalex.org/W2998528465","https://openalex.org/W3024869864","https://openalex.org/W3035305735","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3096831136","https://openalex.org/W3097286738","https://openalex.org/W3104235057","https://openalex.org/W3140429000","https://openalex.org/W3180374548","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4283659485","https://openalex.org/W4294068504","https://openalex.org/W4297808394","https://openalex.org/W4297841405","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4319862479","https://openalex.org/W4319862652","https://openalex.org/W4376653535","https://openalex.org/W4379259581","https://openalex.org/W4381786045","https://openalex.org/W4385574033","https://openalex.org/W4385822683","https://openalex.org/W4385823432","https://openalex.org/W4389520382","https://openalex.org/W4390532523","https://openalex.org/W4390601312","https://openalex.org/W4392908956","https://openalex.org/W4392909760","https://openalex.org/W4393147067","https://openalex.org/W4394671563","https://openalex.org/W4399695892","https://openalex.org/W4401281176","https://openalex.org/W4402112198","https://openalex.org/W4402672020","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6755987414","https://openalex.org/W6767886726","https://openalex.org/W6776442830","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6839738141","https://openalex.org/W6848735303","https://openalex.org/W6852280171","https://openalex.org/W6853165267","https://openalex.org/W6856353250","https://openalex.org/W6860240847","https://openalex.org/W6869989515","https://openalex.org/W6870271299"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4237277701","https://openalex.org/W2121424666","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W1587028174","https://openalex.org/W2358668433","https://openalex.org/W4301250310"],"abstract_inverted_index":{"Representing":[0],"speech":[1,10,13],"with":[2,32],"discrete":[3,23,100,130],"units":[4],"has":[5],"been":[6],"widely":[7],"used":[8],"in":[9,98,109,139],"codec":[11],"and":[12,29,57,66,79,102,132],"generation.":[14],"However,":[15],"there":[16],"are":[17],"several":[18],"unverified":[19],"claims":[20],"about":[21],"self-supervised":[22],"units,":[24,101,131],"such":[25],"as":[26],"disentangling":[27],"phonetic":[28,104],"speaker":[30,93],"information":[31,36,52,60,77,94,105,138],"k-means,":[33],"or":[34],"assuming":[35],"loss":[37],"after":[38,67,86],"k-means.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"take":[44],"an":[45],"information-theoretic":[46],"perspective":[47],"to":[48],"answer":[49],"how":[50,58],"much":[51,59],"is":[53,61,95,106],"present":[54,97,108],"(information":[55,63],"completeness)":[56],"accessible":[62],"accessibility),":[64],"before":[65],"residual":[68,87,141],"vector":[69,88,114],"quantization.":[70,89],"We":[71,90],"show":[72],"a":[73,123,135],"lower":[74],"bound":[75],"for":[76],"completeness":[78,81],"estimate":[80],"on":[82,126],"discretized":[83],"HuBERT":[84,99],"representations":[85],"find":[91],"that":[92,103,113,134],"sufficiently":[96,107],"the":[110,127,140],"residual,":[111],"showing":[112],"quantization":[115],"does":[116],"not":[117],"achieve":[118],"disentanglement.":[119],"Our":[120],"results":[121],"offer":[122],"comprehensive":[124],"assessment":[125],"choice":[128],"of":[129],"suggest":[133],"lot":[136],"more":[137],"should":[142],"be":[143],"mined":[144],"rather":[145],"than":[146],"discarded.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}