{"id":"https://openalex.org/W4385823426","doi":"https://doi.org/10.21437/interspeech.2023-871","title":"Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces","display_name":"Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823426","doi":"https://doi.org/10.21437/interspeech.2023-871"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-871","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/352044473/Self_supervised_Predictive_LIU_DOA17052023_AFV_CC_BY.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110979691","display_name":"Oli Danyi Liu","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":false,"raw_author_name":"Oli Danyi Liu","raw_affiliation_strings":["School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"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":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2968","last_page":"2972"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9607999920845032,"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":0.9607999920845032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.8364695310592651},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7525213956832886},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6754034161567688},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.6581471562385559},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5700576305389404},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.5518707036972046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47246479988098145},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4354028105735779},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.39423808455467224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37547633051872253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13689985871315002},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06626605987548828}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.8364695310592651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525213956832886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6754034161567688},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6581471562385559},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5700576305389404},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.5518707036972046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47246479988098145},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4354028105735779},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.39423808455467224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37547633051872253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13689985871315002},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06626605987548828},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-871","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/7735dc6f-f179-4666-864f-d1f8d3133370","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/352044473/Self_supervised_Predictive_LIU_DOA17052023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, O D, Tang, H & Goldwater, S 2023, Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 2968-2972, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-871","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7735dc6f-f179-4666-864f-d1f8d3133370","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7735dc6f-f179-4666-864f-d1f8d3133370","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, O D, Tang, H & Goldwater, S 2023, Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 2968-2972, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-871","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/7735dc6f-f179-4666-864f-d1f8d3133370","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/352044473/Self_supervised_Predictive_LIU_DOA17052023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, O D, Tang, H & Goldwater, S 2023, Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 2968-2972, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-871","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2119885245","https://openalex.org/W2127958135","https://openalex.org/W2395899413","https://openalex.org/W2972943112","https://openalex.org/W3036601975","https://openalex.org/W3040997499","https://openalex.org/W3140429000","https://openalex.org/W3198815374","https://openalex.org/W3209059054","https://openalex.org/W4225726571","https://openalex.org/W4226380987","https://openalex.org/W4287591426","https://openalex.org/W4294068504","https://openalex.org/W4297808394","https://openalex.org/W4297841405","https://openalex.org/W4311481261","https://openalex.org/W4323066695","https://openalex.org/W4375869060"],"related_works":["https://openalex.org/W2363301696","https://openalex.org/W1622610421","https://openalex.org/W2358167505","https://openalex.org/W2076261188","https://openalex.org/W2120827176","https://openalex.org/W2106898123","https://openalex.org/W4300460695","https://openalex.org/W2377530646","https://openalex.org/W19843487","https://openalex.org/W2390423774"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1],"representations":[2,46],"are":[3,15,28,66],"known":[4],"to":[5,38,45,118],"encode":[6],"both":[7],"speaker":[8,58,77,86,99],"and":[9,59,62,101,114],"phonetic":[10,60],"information,":[11,87],"but":[12],"how":[13],"they":[14,27,65],"distributed":[16],"in":[17,30,106],"the":[18,82,111],"high-dimensional":[19],"space":[20],"remains":[21],"largely":[22],"unexplored.":[23],"We":[24],"hypothesize":[25],"that":[26,35,56,64,84,94],"encoded":[29],"orthogonal":[31],"subspaces,":[32],"a":[33,75,103],"property":[34],"lends":[36],"itself":[37],"simple":[39],"disentanglement.":[40],"Applying":[41],"principal":[42],"component":[43],"analysis":[44],"of":[47,121],"two":[48,54],"predictive":[49],"coding":[50],"models,":[51],"we":[52,73],"identify":[53],"subspaces":[55],"capture":[57],"variances,":[61],"confirm":[63],"nearly":[67],"orthogonal.":[68],"Based":[69],"on":[70],"this":[71],"property,":[72],"propose":[74],"new":[76],"normalization":[78],"method":[79,96],"which":[80],"collapses":[81],"subspace":[83],"encodes":[85],"without":[88],"requiring":[89],"transcriptions.":[90],"Probing":[91],"experiments":[92],"show":[93],"our":[95],"effectively":[97],"eliminates":[98],"information":[100,120],"outperforms":[102],"previous":[104],"baseline":[105],"phone":[107],"discrimination":[108],"tasks.":[109],"Moreover,":[110],"approach":[112],"generalizes":[113],"can":[115],"be":[116],"used":[117],"remove":[119],"unseen":[122],"speakers.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}