{"id":"https://openalex.org/W4385484975","doi":"https://doi.org/10.1109/icasspw59220.2023.10193460","title":"Phone and Speaker Spatial Organization in Self-Supervised Speech Representations","display_name":"Phone and Speaker Spatial Organization in Self-Supervised Speech Representations","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385484975","doi":"https://doi.org/10.1109/icasspw59220.2023.10193460"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5004397011","display_name":"Pablo Riera","orcid":null},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Pablo Riera","raw_affiliation_strings":["Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC), CONICET-UBA,Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC), CONICET-UBA,Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I4210144290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069762064","display_name":"Manuela Cerdeiro","orcid":"https://orcid.org/0000-0002-2673-1851"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Manuela Cerdeiro","raw_affiliation_strings":["Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC), CONICET-UBA,Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC), CONICET-UBA,Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I4210144290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077063899","display_name":"Leonardo Pepino","orcid":"https://orcid.org/0000-0001-5037-3700"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Leonardo Pepino","raw_affiliation_strings":["Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC), CONICET-UBA,Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC), CONICET-UBA,Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I4210144290"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Universidad de Buenos Aires (UBA),Departamento de Computaci&#x00F3;n, FCEyN,Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Buenos Aires (UBA),Departamento de Computaci&#x00F3;n, FCEyN,Argentina","institution_ids":["https://openalex.org/I24354313"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T10860","display_name":"Speech 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/computer-science","display_name":"Computer science","score":0.8122193217277527},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7105109691619873},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6324475407600403},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6131641864776611},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5847212076187134},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5665645003318787},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5187966227531433},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5126623511314392},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4592369496822357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42341727018356323},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42061376571655273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38881632685661316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08662250638008118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122193217277527},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7105109691619873},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6324475407600403},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6131641864776611},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5847212076187134},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5665645003318787},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5187966227531433},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5126623511314392},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4592369496822357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42341727018356323},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42061376571655273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38881632685661316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08662250638008118},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1482790282","https://openalex.org/W1524333225","https://openalex.org/W1635512741","https://openalex.org/W2129957127","https://openalex.org/W2395899413","https://openalex.org/W2407151108","https://openalex.org/W2547875792","https://openalex.org/W2888954148","https://openalex.org/W2889326414","https://openalex.org/W2896457183","https://openalex.org/W2942810103","https://openalex.org/W2982223350","https://openalex.org/W3036601975","https://openalex.org/W3044967013","https://openalex.org/W3096196861","https://openalex.org/W3112034174","https://openalex.org/W3121914243","https://openalex.org/W3162133897","https://openalex.org/W3163596720","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205775916","https://openalex.org/W4206960538","https://openalex.org/W4221145109","https://openalex.org/W4225726571","https://openalex.org/W4226380987","https://openalex.org/W4311137818","https://openalex.org/W6631362777","https://openalex.org/W6679728998","https://openalex.org/W6729448088","https://openalex.org/W6755207826","https://openalex.org/W6761472960","https://openalex.org/W6780218876","https://openalex.org/W6786669483","https://openalex.org/W6788328058","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W37481168","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W1975851543","https://openalex.org/W2070163607"],"abstract_inverted_index":{"Self-supervised":[0],"representations":[1,45,95],"of":[2,13,27,32,86],"speech":[3,94,134,152],"are":[4],"currently":[5],"being":[6],"widely":[7],"used":[8,49,160],"for":[9,50],"a":[10,51,102],"large":[11],"number":[12],"applications.":[14],"Recently,":[15],"some":[16],"efforts":[17],"have":[18,70],"been":[19,71],"made":[20],"in":[21,30,74,91],"trying":[22],"to":[23,41,128],"analyze":[24,82],"the":[25,44,63,75,83,126,133,157],"type":[26],"information":[28,66,90],"present":[29],"each":[31,130],"these":[33,151],"representations.":[34],"Most":[35],"such":[36,114],"work":[37],"uses":[38],"downstream":[39,55,103],"models":[40,149],"test":[42],"whether":[43],"can":[46],"be":[47],"successfully":[48],"specific":[52],"task.":[53],"The":[54],"models,":[56],"though,":[57],"typically":[58],"perform":[59],"nonlinear":[60],"operations":[61],"on":[62,156],"representation":[64,120,131],"extracting":[65],"that":[67,98,148],"may":[68],"not":[69,100],"readily":[72],"available":[73],"original":[76],"representation.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,124],"spatial":[84],"organization":[85],"phone":[87,137],"and":[88,117],"speaker":[89,139],"several":[92],"state-of-the-art":[93],"using":[96,119,141],"methods":[97],"do":[99],"require":[101],"model.":[104],"We":[105],"measure":[106],"how":[107],"different":[108],"layers":[109],"encode":[110],"basic":[111],"acoustic":[112],"parameters":[113],"as":[115],"formants":[116],"pitch":[118],"similarity":[121],"analysis.":[122],"Further,":[123],"study":[125],"extent":[127],"which":[129],"clusters":[132],"samples":[135],"by":[136],"or":[138],"classes":[140],"non-parametric":[142],"statistical":[143],"testing.":[144],"Our":[145],"results":[146],"indicate":[147],"represent":[150],"attributes":[153],"differently":[154],"depending":[155],"target":[158],"task":[159],"during":[161],"pretraining.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-08-03T00:00:00"}
