MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202621062975 A) filed by Symbiosis International Deemed University on May 18, 2026, for Computer-Implemented System And Method For Multilingual Legal Document Translation With Domain-Adaptive Semantic Enrichment And Text-To-Speech.
Inventors include Riya Agrawal; Saumya Kumar; Reuel Menon; and Dr Sudhanshu Gonge.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: ABSTRACT COMPUTER-IMPLEMENTED SYSTEM AND METHOD FOR MULTILINGUAL LEGAL DOCUMENT TRANSLATION WITH DOMAIN-ADAPTIVE SEMANTIC ENRICHMENT AND TEXT-TO-SPEECH The present invention provides a computer-implemented system (100) for multilingual legal document translation with neural audio output. It includes a Processor (201), Memory (203), Network Interface (218), Storage Device (219), Authentication Module (220), and integrated software modules. Documents are authenticated via JSON Web Token verification, format-detected, and processed using OCR or direct text extraction to obtain normalized text. A Language Detection Module (207) identifies the source Indian language, while a Legal Term Detection Module (208) annotates entities using InLegalNER and Aho-Corasick matching. A Semantic Search Module (209) enriches context via a FAISS index, enabling retrieval-augmented translation by the Legal Document Translation Module (210). The Text Refinement Module (211) improves grammar using BART and GECToR. Finally, the Layout Reconstruction Module (212) restores formatting, and the Text-to-Speech Module (213) generates natural-sounding audio output. [
Disclaimer: Curated by HT Syndication.
