Enhancing Identity Protection in Metaverse-Based Psychological Counseling System

Non-face-to-face psychological counseling systems rely on network technologies to anonymize information regarding client identity. However, these systems often face challenges concerning voice data leaks and the suboptimal communication of the client’s non-verbal expressions, such as facial cues, to the counselor. This study proposes a metaverse-based psychological counseling system designed to enhance client identity protection while ensuring efficient information delivery to counselors during non-face-to-face counseling. The proposed system incorporates a voice modulation function that instantly modifies/masks the client’s voice to safeguard their identity. Additionally, it employs real-time client facial expression recognition using an ensemble of decision trees to mirror the client’s non-verbal expressions through their avatar in the metaverse environment. The system is adaptable for use on personal computers and smartphones, offering users the flexibility to access metaverse-based psychological counseling across diverse environments. The performance evaluation of the proposed system confirmed that the voice modulation and real-time facial expression replication consistently achieve an average speed of 48.32 frames per second or higher, even when tested on the least powerful smartphone configurations. Moreover, a total of 550 actual psychological counseling sessions were conducted, and the average satisfaction rating reached 4.46 on a 5-point scale. This indicates that clients experienced improved identity protection compared to conventional non-face-to-face metaverse counseling approaches. Additionally, the counselor successfully addressed the challenge of conveying non-verbal cues from clients who typically struggled with non-face-to-face psychological counseling. The proposed system holds significant potential for applications in interactive discussions and educational activities in the metaverse.