{"id":"https://openalex.org/W4372340923","doi":"https://doi.org/10.1109/icassp49357.2023.10094782","title":"Perceptual Analysis of Speaker Embeddings for Voice Discrimination between Machine And Human Listening","display_name":"Perceptual Analysis of Speaker Embeddings for Voice Discrimination between Machine And Human Listening","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372340923","doi":"https://doi.org/10.1109/icassp49357.2023.10094782"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5060831585","display_name":"Iordanis Thoidis","orcid":"https://orcid.org/0000-0001-6636-4745"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Iordanis Thoidis","raw_affiliation_strings":["Aristotle University of Thessaloniki,School of Electrical and Computer Engineering,Thessaloniki,Greece","School of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,School of Electrical and Computer Engineering,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072191561","display_name":"Cl\u00e9ment Gaultier","orcid":"https://orcid.org/0000-0002-4552-9659"},"institutions":[{"id":"https://openalex.org/I192597271","display_name":"MRC Cognition and Brain Sciences Unit","ror":"https://ror.org/055bpw879","country_code":"GB","type":"facility","lineage":["https://openalex.org/I192597271","https://openalex.org/I241749","https://openalex.org/I4210087105","https://openalex.org/I90344618"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cl\u00e9ment Gaultier","raw_affiliation_strings":["University of Cambridge,Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit,UK","Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit, University of Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit,UK","institution_ids":["https://openalex.org/I192597271"]},{"raw_affiliation_string":"Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit, University of Cambridge, UK","institution_ids":["https://openalex.org/I192597271","https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083391820","display_name":"Tobias Goehring","orcid":"https://orcid.org/0000-0002-9038-3310"},"institutions":[{"id":"https://openalex.org/I192597271","display_name":"MRC Cognition and Brain Sciences Unit","ror":"https://ror.org/055bpw879","country_code":"GB","type":"facility","lineage":["https://openalex.org/I192597271","https://openalex.org/I241749","https://openalex.org/I4210087105","https://openalex.org/I90344618"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tobias Goehring","raw_affiliation_strings":["University of Cambridge,Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit,UK","Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit, University of Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit,UK","institution_ids":["https://openalex.org/I192597271"]},{"raw_affiliation_string":"Cambridge Hearing Group, MRC Cognition and Brain Sciences Unit, University of Cambridge, UK","institution_ids":["https://openalex.org/I192597271","https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55463775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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":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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/discriminative-model","display_name":"Discriminative model","score":0.7674526572227478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7627207040786743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446916699409485},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6644949913024902},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6096653342247009},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5926820039749146},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5405058264732361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.515096127986908},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5095720291137695},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.48515066504478455},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4443441331386566},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.43581920862197876},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42843541502952576},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.41635558009147644},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4146444499492645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3242492079734802}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7674526572227478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7627207040786743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446916699409485},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6644949913024902},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6096653342247009},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5926820039749146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5405058264732361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515096127986908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5095720291137695},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.48515066504478455},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4443441331386566},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.43581920862197876},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42843541502952576},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.41635558009147644},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4146444499492645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3242492079734802},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3314255573","display_name":null,"funder_award_id":"MC_UU_00030/4","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2114925438","https://openalex.org/W2131703294","https://openalex.org/W2168548156","https://openalex.org/W2187089797","https://openalex.org/W2223605538","https://openalex.org/W2558539285","https://openalex.org/W2748318213","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2914866334","https://openalex.org/W2972163809","https://openalex.org/W2972541922","https://openalex.org/W2972598731","https://openalex.org/W3113144688","https://openalex.org/W3133514748","https://openalex.org/W3160950295","https://openalex.org/W3207555018","https://openalex.org/W4280541130","https://openalex.org/W4283817920","https://openalex.org/W4321473516","https://openalex.org/W6631190155","https://openalex.org/W6752888775","https://openalex.org/W6759007826","https://openalex.org/W6850311597"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"the":[3,64,91,94,98,115,130],"information":[4],"captured":[5],"by":[6,56,109],"speaker":[7,24,51,76,99],"embeddings":[8,52,65,77],"with":[9,104],"relevance":[10],"to":[11,21],"human":[12,110,120],"speech":[13],"perception.":[14],"A":[15],"Convolutional":[16],"Neural":[17],"Network":[18],"was":[19],"trained":[20],"perform":[22],"one-shot":[23],"verification":[25],"under":[26],"clean":[27],"and":[28,49,119,125],"noisy":[29],"conditions,":[30],"such":[31,75],"that":[32,47,62,74],"high-level":[33],"abstractions":[34],"of":[35,90],"speaker-specific":[36],"features":[37],"were":[38],"encoded":[39],"in":[40,97],"a":[41,58],"latent":[42],"embedding":[43,100],"vector.":[44],"We":[45],"demonstrate":[46],"robust":[48],"discriminative":[50],"can":[53],"be":[54],"obtained":[55],"using":[57],"training":[59],"loss":[60],"function":[61],"optimizes":[63],"for":[66,133],"similarity":[67],"scoring":[68],"during":[69],"inference.":[70],"Computational":[71],"analysis":[72],"showed":[73],"predicted":[78],"various":[79],"hand-crafted":[80],"acoustic":[81],"features,":[82],"while":[83],"no":[84],"single":[85],"feature":[86],"explained":[87],"substantial":[88],"variance":[89],"embeddings.":[92],"Moreover,":[93],"relative":[95],"distances":[96],"space":[101],"moderately":[102],"coincided":[103],"voice":[105],"similarity,":[106],"as":[107],"inferred":[108],"listeners.":[111],"These":[112],"findings":[113],"confirm":[114],"overlap":[116],"between":[117],"machine":[118],"listening":[121],"when":[122],"discriminating":[123],"voices":[124],"motivate":[126],"further":[127],"research":[128],"on":[129],"remaining":[131],"disparities":[132],"improving":[134],"model":[135],"performance.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}