{"id":"https://openalex.org/W4410770311","doi":"https://doi.org/10.1109/icasspw65056.2025.11011236","title":"Discrete Speech Unit Extraction via Independent Component Analysis","display_name":"Discrete Speech Unit Extraction via Independent Component Analysis","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410770311","doi":"https://doi.org/10.1109/icasspw65056.2025.11011236"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023799668","display_name":"Kwanghee Choi","orcid":"https://orcid.org/0000-0001-5254-1093"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwanghee Choi","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310816","display_name":"Keigo Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keigo Hojo","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098968","display_name":"Satoru Fukayama","orcid":"https://orcid.org/0000-0001-6506-2796"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Fukayama","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9929999709129333,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9929999709129333,"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":0.9825999736785889,"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/independent-component-analysis","display_name":"Independent component analysis","score":0.7059495449066162},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6532608270645142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.628052830696106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5027837753295898},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.44642260670661926},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.43322473764419556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.358100950717926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.310499370098114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21085196733474731},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07827860116958618},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.07581555843353271}],"concepts":[{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.7059495449066162},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6532608270645142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.628052830696106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5027837753295898},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.44642260670661926},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.43322473764419556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.358100950717926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.310499370098114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21085196733474731},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07827860116958618},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.07581555843353271},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W108815450","https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W2143132653","https://openalex.org/W2946521785","https://openalex.org/W2970172244","https://openalex.org/W3139958517","https://openalex.org/W3180374548","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W3213029956","https://openalex.org/W4226033575","https://openalex.org/W4226380987","https://openalex.org/W4285250921","https://openalex.org/W4287854499","https://openalex.org/W4296069362","https://openalex.org/W4319862255","https://openalex.org/W4375868953","https://openalex.org/W4375869060","https://openalex.org/W4375869259","https://openalex.org/W4381786045","https://openalex.org/W4385570550","https://openalex.org/W4385822439","https://openalex.org/W4385822683","https://openalex.org/W4385823003","https://openalex.org/W4389518770","https://openalex.org/W4392902623","https://openalex.org/W4392903098","https://openalex.org/W4392904805","https://openalex.org/W4392909068","https://openalex.org/W4402111789","https://openalex.org/W4402112125","https://openalex.org/W4402112198","https://openalex.org/W4405532155","https://openalex.org/W4406461488","https://openalex.org/W6674733807","https://openalex.org/W6734040793","https://openalex.org/W6780218876","https://openalex.org/W6790356757","https://openalex.org/W6794146050","https://openalex.org/W6845712036","https://openalex.org/W6852781825","https://openalex.org/W6853998256"],"related_works":["https://openalex.org/W2121429698","https://openalex.org/W2182042810","https://openalex.org/W4252230435","https://openalex.org/W55679925","https://openalex.org/W3080404860","https://openalex.org/W2046761971","https://openalex.org/W3144722888","https://openalex.org/W2364896863","https://openalex.org/W2389189059","https://openalex.org/W4288804231"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,11,24,33,54],"models":[2],"(S3Ms)":[3],"have":[4],"become":[5],"a":[6],"common":[7],"tool":[8],"for":[9,16,32,71,96,121],"the":[10,60,81,90],"processing":[12],"community,":[13],"leveraging":[14],"representations":[15,21,31,70],"downstream":[17],"tasks.":[18],"Clustering":[19],"S3M":[20,66,69],"yields":[22],"discrete":[23],"units":[25],"(DSUs),":[26],"which":[27],"serve":[28],"as":[29,119,132],"compact":[30],"signals.":[34],"DSUs":[35,43],"are":[36],"typically":[37],"obtained":[38],"by":[39],"k-means":[40],"clustering.":[41],"Using":[42],"often":[44],"leads":[45],"to":[46],"strong":[47],"performance":[48],"in":[49],"various":[50],"tasks,":[51],"including":[52],"automatic":[53],"recognition":[55],"(ASR).":[56],"However,":[57],"even":[58,76],"with":[59],"high":[61],"dimensionality":[62],"and":[63,106,115],"redundancy":[64],"of":[65,83,92,128,136,139],"representations,":[67],"preprocessing":[68,94,120],"better":[72],"clustering":[73],"remains":[74],"unexplored,":[75],"though":[77],"it":[78],"can":[79],"affect":[80],"quality":[82],"DSUs.":[84,98],"In":[85],"this":[86],"paper,":[87],"we":[88],"investigate":[89],"potential":[91],"linear":[93],"methods":[95],"extracting":[97],"We":[99,123],"evaluate":[100],"standardization,":[101],"principal":[102],"component":[103,108],"analysis,":[104],"whitening,":[105],"independent":[107],"analysis":[109],"(ICA)":[110],"on":[111],"DSU-based":[112],"ASR":[113],"benchmarks":[114],"demonstrate":[116],"their":[117,129],"effectiveness":[118],"k-means.":[122],"also":[124],"conduct":[125],"extensive":[126],"analyses":[127],"behavior,":[130],"such":[131],"orthogonality":[133],"or":[134],"interpretability":[135],"individual":[137],"components":[138],"ICA.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}