MUMBAI, India, Aug. 8 -- Intellectual Property India has published a patent application (202441006991 A) filed by Samsung Electronics Co. Ltd., Gyeonggi, Republic of Korea, on Feb. 2, 2024, for 'method and system for processing a voice input in voice assistant devices.'
Inventor(s) include Debojyoti Saha; Krishna Singh; Vinay Vasanth Patage; and Javaid Nabi.
The application for the patent was published on Aug. 8, under issue no. 32/2025.
According to the abstract released by the Intellectual Property India: "The present disclosure relates to a method and apparatus for processing a voice input. The method includes determining a first candidate text output from a list of candidate text outputs generated in response to a user's voice input. Validating feasibility of executing the first candidate text output. 10 If execution is not feasible, failure information is determined. Further, a second list of candidate text outputs and corresponding text embeddings is generated, and a second candidate text output is then selected from second list of candidates based on the correlation of text embeddings with the voice input's audio embedding, and the corresponding action is executed. The present disclosure provides a voice assistant device (100) and method for processing voice inputs in the 15 voice assistant device (100), auto-enhancing accuracy of voice input recognition and action execution."
Disclaimer: Curated by HT Syndication.
