MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611113244 A) filed by Chandigarh University on September 22, 2026, for Prosody-Preserving Cross-Lingual Neural Voice Synchronization System For Real-Time Emotional Communication.
Inventors include Shaman Sharma; Manoj Gaur; Rishi Kumar; and Deepak Kumar.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: Prosody-Preserving Cross-Lingual Neural Voice Synchronization System for Real-Time Emotional Communication. The invention relates to neural speech processing for real-time multilingual communication. A distributed system captures live speech through an audio input device and separates linguistic content from style information, including acoustic and emotional characteristics. A translation engine converts the content representation into a target-language representation, while a vector database stores and retrieves voice embeddings and emotional profiles. A persona selector selects an original or alternative acoustic persona, and a voice synthesizer combines the selected style representation with translated content to generate target-language speech. A latency optimizer coordinates edge processing and cloud processing, and user devices receive concurrent personalized audio streams. The arrangement provides real-time cross-lingual speech generation with preserved or selected acoustic character
Disclaimer: Curated by HT Syndication.
