This study presents an approach for developing digital avatars replicating individuals’ physical characteristics and communicative style, contributing to research on virtual interactions in the metaverse. The proposed method integrates large language models (LLMs) with 3D avatar creation techniques, using what we call the Tree of Style (ToS) methodology to generate stylistically consistent and contextually appropriate responses. Linguistic analysis and personalized voice synthesis enhance conversational and auditory realism. The results suggest that ToS offers a practical alternative to fine-tuning for creating stylistically accurate responses while maintaining efficiency. This study outlines potential applications and acknowledges the need for further work on adaptability and ethical considerations.
Nasser, M., Gaglio, G.F., Seidita, V., Chella, A. (2025). The Art of Replication: Lifelike Avatars with Personalized Conversational Style. ROBOTICS, 14(3) [10.3390/robotics14030033].
The Art of Replication: Lifelike Avatars with Personalized Conversational Style
Nasser, Michele
;Gaglio, Giuseppe Fulvio;Seidita, Valeria;Chella, Antonio
2025-03-01
Abstract
This study presents an approach for developing digital avatars replicating individuals’ physical characteristics and communicative style, contributing to research on virtual interactions in the metaverse. The proposed method integrates large language models (LLMs) with 3D avatar creation techniques, using what we call the Tree of Style (ToS) methodology to generate stylistically consistent and contextually appropriate responses. Linguistic analysis and personalized voice synthesis enhance conversational and auditory realism. The results suggest that ToS offers a practical alternative to fine-tuning for creating stylistically accurate responses while maintaining efficiency. This study outlines potential applications and acknowledges the need for further work on adaptability and ethical considerations.File | Dimensione | Formato | |
---|---|---|---|
robotics-14-00033.pdf
accesso aperto
Descrizione: This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/ licenses/by/4.0/
Tipologia:
Versione Editoriale
Dimensione
2.43 MB
Formato
Adobe PDF
|
2.43 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.