{"id":"https://openalex.org/W4372260421","doi":"https://doi.org/10.1109/icassp49357.2023.10095119","title":"An Isotropy Analysis for Self-Supervised Acoustic Unit Embeddings on the Zero Resource Speech Challenge 2021 Framework","display_name":"An Isotropy Analysis for Self-Supervised Acoustic Unit Embeddings on the Zero Resource Speech Challenge 2021 Framework","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260421","doi":"https://doi.org/10.1109/icassp49357.2023.10095119"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095119","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},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":"https://doi.org/10.1109/icassp49357.2023.10095119","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100701917","display_name":"Jianan Chen","orcid":"https://orcid.org/0000-0002-4607-3227"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianan Chen","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":67},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998,"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":0.9998,"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":0.9942,"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":0.9937,"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/zero","display_name":"Zero (linguistics)","score":0.6134184}],"concepts":[{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.69151074},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6134184},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.59927195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.544061},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.51672715},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47121304},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3319288},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25321394},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2274462},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10916698},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.07767594},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095119","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}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095119","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},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.68,"id":"https://metadata.un.org/sdg/10"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2933138175","https://openalex.org/W2973026522","https://openalex.org/W2988217457","https://openalex.org/W2995181338","https://openalex.org/W3093096176","https://openalex.org/W3104162037","https://openalex.org/W3156636935","https://openalex.org/W3197259906","https://openalex.org/W3197349023","https://openalex.org/W3197381195","https://openalex.org/W3197580070","https://openalex.org/W3205727812","https://openalex.org/W3209059054","https://openalex.org/W4292825791","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W4382753160","https://openalex.org/W4320084277","https://openalex.org/W4298134547","https://openalex.org/W2794789911","https://openalex.org/W2284229495","https://openalex.org/W2122976425","https://openalex.org/W2088773039","https://openalex.org/W2028697747","https://openalex.org/W1994881304","https://openalex.org/W1559463472"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"self-supervised":[3,20,65,110],"representation":[4,21,111],"learning":[5,22],"has":[6],"gained":[7],"much":[8],"attention":[9],"for":[10],"its":[11],"proven":[12],"advantages":[13],"in":[14,51,55,73,158],"many":[15],"downstream":[16],"tasks.":[17],"Consequently,":[18],"various":[19],"methods":[23],"have":[24,30],"been":[25],"developed.":[26],"However,":[27],"few":[28],"studies":[29],"investigated":[31],"the":[32,53,58,71,78,90,97,146,150,159],"resulting":[33],"embedding":[34,61,124],"space":[35],"or":[36],"analyzed":[37],"why":[38],"any":[39,45],"particular":[40],"approach":[41],"performs":[42],"better":[43],"than":[44],"other.":[46],"Here,":[47,103],"we":[48,104,114,131],"are":[49,94],"interested":[50],"investigating":[52],"geometry":[54],"terms":[56],"of":[57,60,120,123],"isotropy":[59],"spaces":[62],"learned":[63],"by":[64],"speech":[66],"representation,":[67],"which":[68,126],"can":[69],"influence":[70,128],"performance":[72],"discriminating":[74],"acoustic":[75],"units":[76],"on":[77,96],"Zero":[79],"Resource":[80],"Speech":[81],"Challenge":[82],"2021":[83],"(ZR2021)":[84],"framework.":[85],"Most":[86],"top":[87,156],"systems":[88],"from":[89],"published":[91],"ZR2021":[92,160],"results":[93],"based":[95],"contrastive":[98],"predictive":[99],"coding":[100],"(CPC)":[101],"technique.":[102],"propose":[105],"using":[106],"hidden-unit":[107],"BERT":[108],"(HuBERT)":[109],"learning,":[112],"and":[113,118,154],"provide":[115],"detailed":[116],"analyses":[117],"comparisons":[119],"their":[121],"isotropies":[122],"space,":[125],"might":[127],"performance.":[129],"Furthermore,":[130],"use":[132],"simple":[133],"yet":[134],"effective":[135],"feature":[136],"fusion":[137],"techniques":[138],"to":[139,145,148],"combine":[140],"both":[141],"models'":[142],"strengths,":[143],"leading":[144],"ability":[147],"reduce":[149],"ABX":[151],"error":[152],"rate":[153],"outperform":[155],"models":[157],"dev-other":[161],"dataset.":[162]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4372260421","counts_by_year":[],"updated_date":"2025-01-06T05:14:24.423428","created_date":"2023-05-07"}