MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611083832 A) filed by Amrita Vishwa Vidyapeetham on July 08, 2026, for Multilingual Speech Processing With Speaker Separation And Clinical Document Generation.
Inventors include Bijlani, Kamal; Soni, Vijay Kumar; Kumar, Abhishek; and Soni, Sumit.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: The present disclosure relates to a multilingual clinical documentation system (100) and a method (400). The system (100) includes at least one audio capture device (102), a speech processing engine (108) converting concurrent audio streams from a first speaker (104) and a second speaker (106) into text using language-specific acoustic models (110), a speaker diarization unit (112) labeling each utterance based on acoustic features (114) and turn patterns (116) without prior voice enrollment, a translation engine (118) translating utterances in real time using a clinical ontology database (124), a text to speech unit (120) converting translated utterances into audio output, and a document generation engine (122) simultaneously generating a prescription (130), a Subjective Objective Assessment Plan note (126), and a discharge summary (132) from a single consultation transcript. Unlike conventional single-language documentation systems, the present system (100) addresses multilingual communication barriers and physician documentation burden in multilingual healthcare environments.
Disclaimer: Curated by HT Syndication.
