Intellectual Property India Publishes Patent Application for 'Audio-Based Gender, Emotion Recognition, Transcript Generation And Speaker Diarization Using Deep Learning Algorithms' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122807 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'audio-based gender, emotion recognition, transcript generation and speaker diarization using deep learning algorithms.'

Inventor(s) include Prof. R. Mariappan; Tetali Durga Venkata Reddy; Kodumuri Venkat Rohith; and Kandibanda Rathan Sai.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides an integrated audio processing system comprising an audio input module configured to receive audio signals containing speech from one or more speakers, a convolutional neural network (CNN) module configured to extract spatial features from the audio signals, a bidirectional long short-term memory (Bi-LSTM) module configured to capture temporal dependencies from the spatial features extracted by the CNN module, a gender classification module configured to classify speaker gender using the CNN and Bi-LSTM modules, an emotion recognition module configured to identify emotional states using the CNN and Bi-LSTM modules, a transcript generation module configured to convert speech to text using automatic speech recognition, a speaker diarization module configured to segment the audio signals by speaker identity, and an output module configured to generate integrated results comprising the gender classification, emotion recognition, transcript, and speaker diarization results."

Disclaimer: Curated by HT Syndication.