[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-459062-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-459062-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","reconstructing-voice-identity-from-noninvasive-auditory-cortex-recordings","Reconstructing voice identity from noninvasive auditory cortex recordings","","Voice information processing engages temporal voice areas that respond preferentially to conspecific vocalizations, yet the neural representation of speaker identity within these areas remains poorly characterized. The study trains a deep neural network to construct a compact voice identity representational space and tests its alignment with fMRI activity using encoding, representational similarity, and decoding. Results show improved account of TVA identity geometry and reconstructions preserving identity-relevant characteristics verified by classifiers and human listeners.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/reconstructing-voice-identity-from-noninvasive-auditory-cortex-recordings/459062/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/reconstructing-voice-identity-from-noninvasive-auditory-cortex-recordings/459062.png","ImageObject",300,407,{"name":42,"@type":43},"hdkawk","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What neural and computational approach is used to model voice identity?","Question",{"text":63,"@type":64},"A deep neural network is trained to generate a compact representational space for voice identity, which is linked to brain activity using encoding, representational similarity, and decoding analyses.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What brain signals are analyzed in relation to the voice latent space?",{"text":68,"@type":64},"The study examines fMRI responses in auditory cortex and temporal voice areas, assessing how the derived identity space relates to representational content in these regions.",{"name":70,"@type":61,"acceptedAnswer":71},"How are voice stimuli reconstructions evaluated?",{"text":72,"@type":64},"Reconstructions based on temporal voice area information are assessed using both machine classifiers and human listeners, focusing on whether essential aspects of speaker identity are preserved.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},459062,1790814803,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":97,"preview_urls":146},3985747859855,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","RESEARCH ARTICLE  \n*For correspondence:  \n[charlylmth@gmail.com](charlylmth@gmail.com) (CL);  \n[thierry.artieres@univ-amu.fr](thierry.artieres@univ-amu.fr) (TA); [pascal.belin@univ-amu.fr](pascal.belin@univ-amu.fr) (PB)  \nCompeting interest: The authors declare that no competing interests exist.  \nFunding: See page 19  \nPreprint posted  \n19 March 2024  \nSent for Review  \n16 April 2024  \nReviewed preprint posted  \n15 July 2024  \nReviewed preprint revised  \n20 November 2025  \nVersion of Record published  \n08 January 2026  \nReviewing Editor: Andrea E Martin, Max Planck Institute for Psycholinguistics, Netherlands  \n Copyright Lamothe et al. This article is distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use andredistribution provided that the original author and source are credited.  \nReconstructing voice identity from noninvasive auditory cortex recordings  \nCharly Lamothe1,2*, Etienne Thoret1,2,3,4, Régis Trapeau1, Bruno L Giordano1, Julien Sein1,5, Sylvain Takerkart1, Stephane Ayache2, Thierry Artieres2,6*, Pascal Belin1*  \n1 La Timone Neuroscience Institute UMR 7289, CNRS, Aix-Marseille University, Marseille, France; 2 Laboratoire d’Informatique et Systèmes UMR 7020, CNRS, Aix-Marseille University, Marseille, France; 3 Perception, Representation, Image, Sound, Music UMR 7061, CNRS, Marseille, France; 4 Institute of Language Communication & the Brain, Marseille, France; 5Centre IRM-INT@CERIMED, Marseille, France; 6 École Centrale de Marseille, Marseille, France  \n\n| eLife Assessment\u003Cbr>This study used deep neural networks (DNN) to reconstruct voice information (viz., speaker identity), from fMRI responses in the auditory cortex and temporal voice areas, and assessed the representational content in these areas with decoding. A DNN-derived feature space approximated the neural representation of speaker identity-related information. The findings are valuable and the approach solid, yielding insight into how a specific model architecture can be used to relate the latent spaces of neural data and auditory stimuli to each other. |\n| --- |\n| Abstract The cerebral processing of voice information is known to engage, in human as well as non-human primates,‘temporal voice areas’(TVAs) that respond preferentially to conspecific vocalizations. However, how voice information is represented by neuronal populations in these areas, particularly speaker identity information, remains poorly understood. Here, we used a deep neural network (DNN) to generate a high-level, small-dimension representational space for voice identity—the ‘voice latent space’(VLS)—and examined its linear relation with cerebral activity via encoding, representational similarity, and decoding analyses. We find that the VLS maps onto fMRI measures of cerebral activity in response to tens of thousands of voice stimuli from hundreds of different speaker identities and better accounts for the representational geometry for speaker identity in the TVAs than in A1 . Moreover, the VLS allowed TVA-based reconstructions of voice stimuli that preserved essential aspects of speaker identity as assessed by both machine classifiers and human listeners. These results indicate that the DNN-derived VLS provides high-level representations of voice identity information in the TVAs. |\n\nIntroduction  \nThe human voice carries speech, but is also an ‘auditory face’uent that carries much valuable information on the stable physical characteristics of the speaker (hereafter,‘identity-related’; Belin et al., 2004; Belin et al., 2011) . The ability of listeners to extract identity-related information from a voice such as gender, age, or unique identity even in brief stimuli plays a crucial role in our social interactions. Yet, its neural bases remain poorly understood compared to those of speech processing. Studies over the past two decades have clearly established via complementary neuroimaging techniques that the cerebral processing of voice infor","cbCaic7fD0TK3vKd","https://ap.wps.com/l/cbCaic7fD0TK3vKd","pdf",4931337,42,"English","# Abstract\n# Introduction\n## Temporal voice areas and voice identity\n## Deep neural networks for auditory representation and decoding","[{\"question\":\"What neural and computational approach is used to model voice identity?\",\"answer\":\"A deep neural network is trained to generate a compact representational space for voice identity, which is linked to brain activity using encoding, representational similarity, and decoding analyses.\"},{\"question\":\"What brain signals are analyzed in relation to the voice latent space?\",\"answer\":\"The study examines fMRI responses in auditory cortex and temporal voice areas, assessing how the derived identity space relates to representational content in these regions.\"},{\"question\":\"How are voice stimuli reconstructions evaluated?\",\"answer\":\"Reconstructions based on temporal voice area information are assessed using both machine classifiers and human listeners, focusing on whether essential aspects of speaker identity are preserved.\"}]","Reconstructing voice identity from noninvasive auditory cortex recordings | PDF",1790755119,106,[147,151,155,159,163],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/04042f83a5cae8b53f09b84f3773f46d.webp",983,1272,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/22d82e0261db53f31c7fe088b496ed66.webp",982,1270,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/966b34e7a4a9fbb8814e1da93a36a6f9.webp",981,1269,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/8b0da830401c68fb5784ea3bc0b4ecad.webp",980,1268,{"page_no":97,"url":164,"width":165,"height":166},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/1105a6e8af004c3622dfaf93ca1f1c6e.webp",979,1267]