MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641048889 A) filed by Agni College Of Technology, Chennai, Tamil Nadu, on April 17, for 'ai-framework for generating human facial and body features from speech.'
Inventor(s) include Prinslin L; Deepak P; Hariharan R; Jayanadh S; and Livin Kumar R.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to an Artificial Intelligence based framework for generating human facial and body features from speech input. The system is designed to analyze acoustic characteristics of a person's voice, including pitch, tone, frequency, accent, speaking style, and emotional patterns, in order to predict corresponding physical attributes. By utilizing advanced machine learning and deep learning algorithms, the invention establishes a relationship between speech signals and visual human characteristics such as face shape, skin tone, hairstyle, facial expression, age group, gender traits, and body structure. The predicted attributes are further processed through generative models to create realistic digital facial images, body representations, or avatars. The invention provides an automated and efficient alternative to conventional manual methods such as forensic sketching, questionnaire-based avatar design, and character modeling. It improves speed, scalability, and accuracy while reducing hum."
Disclaimer: Curated by HT Syndication.
