MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521130795 A) filed by Symbiosis International, Pune, Maharashtra, on Dec. 23, 2025, for 'system and method for speaker identification and emotion detection from speech.'
Inventor(s) include Nitya Sharma; Nithish Ragavendara H; and Dr. Deepali Vora.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "A computer-implemented system (100) and method (200) for speaker identification and emotion detection from speech signals are disclosed. The system (100) receives speech input and converts the speech into Mel-spectrogram representations (101) for feature analysis. Convolutional Neural Network (CNN) layers (102) are employed to extract spatial acoustic features for accurate speaker identification, while Long Short-Term Memory (LSTM) layers model (105) temporal dependencies in the speech signals for emotion detection. The method (200) includes receiving speech input (201), preprocessing and Mel-spectrogram conversion (202), CNN-based speaker classification, LSTM-based temporal modelling (208), and outputting identified speaker (205) and detected emotion results (206). The invention provides a unified framework that reduces reliance on manual feature extraction and achieves improved accuracy, efficiency, and real-time performance, making it suitable for voice-based authentication and emotion-aware human-machine interaction systems."
Disclaimer: Curated by HT Syndication.
