MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202421002657 A) filed by Walchand College Of Engineering on January 13, 2024, for Emotion-Enhanced Multilingual Text-To-Speech System With User Customization Capabilities..
Inventors include Dr. B. F. Momin; Mr. Devang Kamble; Mr. Teknath Jha; Ms. Vaishnavi Mahajan; and Akanksha Chaudhari.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: This invention describes a. Text-to-Speech System for Emotionally Resonant, Multilingual, and Highly Customizable Voice Outputs is an innovative technology revolutionizing machine-generated speech. This system incorporates an emotion synthesis module, leveraging facial expression recognition and voice tone analysis, to dynamically modulate speech based on detected or user-specified emotions. A robust multilingual and transliteration engine supports diverse languages, offering accurate pronunciation and natural phonetic rendering. The voice cloning module enhances personalization, allowing users to input voice samples for customized synthesis. Continuous learning mechanisms refine emotional responses and voice characteristics over time, adapting to individual preferences. The system's adaptive language recognition algorithm ensures seamless handling of unknown languages. With applications ranging from emotional support to language learning, this Text-to-Speech system represents a significant advancement in user-centric, emotionally resonant machine-generated speech.
Disclaimer: Curated by HT Syndication.
