fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses

Abstract With the advancement of artificial intelligence (AI) speech synthesis technology, its application in personalized voice services and its potential role in emotional comfort have become research focal points. This study aims to explore the impact of AI-synthesized familiar and unfamiliar voi...

Full description

Saved in:
Bibliographic Details
Main Authors: Weijia Zhang, Jiaju Li, Luyang Ji, Xue Cheng, Dongqin Sun, Yanrong Jiang, Feiyu Chen, Yiduo Zhou, Calvin Choi, Hao Cheng, Shaomin Cai
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92702-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850272912894853120
author Weijia Zhang
Jiaju Li
Luyang Ji
Xue Cheng
Dongqin Sun
Yanrong Jiang
Feiyu Chen
Yiduo Zhou
Calvin Choi
Hao Cheng
Shaomin Cai
author_facet Weijia Zhang
Jiaju Li
Luyang Ji
Xue Cheng
Dongqin Sun
Yanrong Jiang
Feiyu Chen
Yiduo Zhou
Calvin Choi
Hao Cheng
Shaomin Cai
author_sort Weijia Zhang
collection DOAJ
description Abstract With the advancement of artificial intelligence (AI) speech synthesis technology, its application in personalized voice services and its potential role in emotional comfort have become research focal points. This study aims to explore the impact of AI-synthesized familiar and unfamiliar voices on neural responses in the brain. We utilized the GPT-SoVITS project to synthesize three types of voices: a female voice, a sweet female voice, and a maternal voice, all reading the same text. Using functional near-infrared spectroscopy (fNIRS), we monitored the changes in blood oxygen levels in the prefrontal cortex and temporal cortex of participants during listening, assessing brain activation. The experimental results showed that the AI-synthesized maternal voice significantly activated the participants’ prefrontal and temporal cortices. Combined with participants’ feedback, the activation of these areas may reflect multidimensional features of voice familiarity processing, including emotion, memory, and cognitive function. This finding reveals the potential applications of AI voice technology in enhancing mental health and user experience.
format Article
id doaj-art-cbf3911cfd254cddbf25b05bb59b4458
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-cbf3911cfd254cddbf25b05bb59b44582025-08-20T01:51:39ZengNature PortfolioScientific Reports2045-23222025-05-0115111610.1038/s41598-025-92702-5fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responsesWeijia Zhang0Jiaju Li1Luyang Ji2Xue Cheng3Dongqin Sun4Yanrong Jiang5Feiyu Chen6Yiduo Zhou7Calvin Choi8Hao Cheng9Shaomin Cai10Department of Mathematica and Information Sciences, Shaoxing UniversityDepartment of Mathematica and Information Sciences, Shaoxing UniversityDepartment of Mathematica and Information Sciences, Shaoxing UniversityDepartment of Mathematica and Information Sciences, Shaoxing UniversityDepartment of Mathematica and Information Sciences, Shaoxing UniversityDepartment of Mathematica and Information Sciences, Shaoxing UniversityDepartment of Mathematica and Information Sciences, Shaoxing UniversityDepartment of Mathematica and Information Sciences, Shaoxing UniversityOxford Industrial Holding GroupZhejiang Chengshi Metaverse Technology Co., LtdSchool of Medicine, Shaoxing UniversityAbstract With the advancement of artificial intelligence (AI) speech synthesis technology, its application in personalized voice services and its potential role in emotional comfort have become research focal points. This study aims to explore the impact of AI-synthesized familiar and unfamiliar voices on neural responses in the brain. We utilized the GPT-SoVITS project to synthesize three types of voices: a female voice, a sweet female voice, and a maternal voice, all reading the same text. Using functional near-infrared spectroscopy (fNIRS), we monitored the changes in blood oxygen levels in the prefrontal cortex and temporal cortex of participants during listening, assessing brain activation. The experimental results showed that the AI-synthesized maternal voice significantly activated the participants’ prefrontal and temporal cortices. Combined with participants’ feedback, the activation of these areas may reflect multidimensional features of voice familiarity processing, including emotion, memory, and cognitive function. This finding reveals the potential applications of AI voice technology in enhancing mental health and user experience.https://doi.org/10.1038/s41598-025-92702-5Artificial intelligenceHuman-computer interactionVoice synthesisSocial impact of synthetic speechfNIRS
spellingShingle Weijia Zhang
Jiaju Li
Luyang Ji
Xue Cheng
Dongqin Sun
Yanrong Jiang
Feiyu Chen
Yiduo Zhou
Calvin Choi
Hao Cheng
Shaomin Cai
fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses
Scientific Reports
Artificial intelligence
Human-computer interaction
Voice synthesis
Social impact of synthetic speech
fNIRS
title fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses
title_full fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses
title_fullStr fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses
title_full_unstemmed fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses
title_short fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses
title_sort fnirs experimental study on the impact of ai synthesized familiar voices on brain neural responses
topic Artificial intelligence
Human-computer interaction
Voice synthesis
Social impact of synthetic speech
fNIRS
url https://doi.org/10.1038/s41598-025-92702-5
work_keys_str_mv AT weijiazhang fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT jiajuli fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT luyangji fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT xuecheng fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT dongqinsun fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT yanrongjiang fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT feiyuchen fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT yiduozhou fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT calvinchoi fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT haocheng fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses
AT shaomincai fnirsexperimentalstudyontheimpactofaisynthesizedfamiliarvoicesonbrainneuralresponses