{"id":"https://openalex.org/W4392903423","doi":"https://doi.org/10.1109/icassp48485.2024.10446197","title":"Towards an Interpretable Representation of Speaker Identity via Perceptual Voice Qualities","display_name":"Towards an Interpretable Representation of Speaker Identity via Perceptual Voice Qualities","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903423","doi":"https://doi.org/10.1109/icassp48485.2024.10446197"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5093013842","display_name":"Robin Netzorg","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robin Netzorg","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111063140","display_name":"Bohan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bohan Yu","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018569458","display_name":"Andrea L. Guzman","orcid":"https://orcid.org/0000-0002-6874-9435"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Guzman","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081837203","display_name":"Peter Wu","orcid":"https://orcid.org/0000-0001-6503-3936"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Wu","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093013843","display_name":"Luna McNulty","orcid":null},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luna McNulty","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala Krishna Anumanchipalli","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5093013842"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73081414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12391","last_page":"12395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7691947221755981},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.7120264768600464},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6739926338195801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6267865300178528},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5932270884513855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.510765790939331},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5070903301239014},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.46703195571899414},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44729408621788025},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.43745899200439453},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.428419291973114},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.422402024269104},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2859729528427124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07809954881668091}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7691947221755981},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.7120264768600464},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6739926338195801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6267865300178528},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5932270884513855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.510765790939331},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5070903301239014},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.46703195571899414},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44729408621788025},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.43745899200439453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.428419291973114},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.422402024269104},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2859729528427124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07809954881668091},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1974031554","https://openalex.org/W1994997260","https://openalex.org/W2011585205","https://openalex.org/W2058411003","https://openalex.org/W2082927806","https://openalex.org/W2176409853","https://openalex.org/W2315535101","https://openalex.org/W2330562562","https://openalex.org/W2890964092","https://openalex.org/W3011778067","https://openalex.org/W3093575194","https://openalex.org/W3137249133","https://openalex.org/W3209059054","https://openalex.org/W4221147462","https://openalex.org/W4225329057","https://openalex.org/W4226181439","https://openalex.org/W4283325792","https://openalex.org/W4310067961","https://openalex.org/W4312055902","https://openalex.org/W4365503441","https://openalex.org/W4372340876"],"related_works":["https://openalex.org/W4251972423","https://openalex.org/W2185469136","https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W4313320911","https://openalex.org/W2383401824"],"abstract_inverted_index":{"Unlike":[0],"other":[1],"data":[2],"modalities":[3],"such":[4,41],"as":[5,42],"text":[6],"and":[7,101,123],"vision,":[8],"speech":[9,34,138],"does":[10],"not":[11],"lend":[12],"itself":[13],"to":[14,23,68,109],"easy":[15],"interpretation.":[16],"While":[17],"lay":[18],"people":[19],"can":[20],"understand":[21],"how":[22],"describe":[24],"an":[25,94],"image":[26],"or":[27,44,105],"sentence":[28],"via":[29],"perception,":[30],"non-expert":[31],"descriptions":[32],"of":[33,55,74,86,89,96,121],"often":[35],"end":[36],"at":[37],"high-level":[38,99],"demographic":[39],"information,":[40],"gender":[43],"age.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,112],"propose":[50],"a":[51,82,131],"possible":[52],"interpretable":[53],"representation":[54,133],"speaker":[56],"identity":[57],"based":[58],"on":[59],"perceptual":[60,83],"voice":[61],"qualities":[62],"(PQs).":[63],"By":[64],"adding":[65],"gendered":[66],"PQs":[67,116],"the":[69,87,127],"pathology-focused":[70],"Consensus":[71],"Auditory-Perceptual":[72],"Evaluation":[73],"Voice":[75],"(CAPE-V)":[76],"protocol,":[77],"our":[78],"PQ-based":[79,132],"approach":[80],"provides":[81],"latent":[84],"space":[85],"character":[88],"adult":[90],"voices":[91],"that":[92,114,126],"is":[93,134],"intermediary":[95],"abstraction":[97],"between":[98],"demographics":[100],"low-level":[102],"acoustic,":[103],"physical,":[104],"learned":[106],"representations.":[107,139],"Contrary":[108],"prior":[110],"belief,":[111],"demonstrate":[113,125],"these":[115],"are":[117],"hearable":[118],"by":[119,136],"ensembles":[120],"non-experts,":[122],"further":[124],"information":[128],"encoded":[129],"in":[130],"predictable":[135],"various":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
