MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521130742 A) filed by Symbiosis International, Pune, Maharashtra, on Dec. 23, 2025, for 'system and method for detecting artificial intelligence generated voice using hybrid acoustic and linguistic analysis.'
Inventor(s) include Dr Latika Pinjarkar; Harshini Bonde; Vedant Nawghare; and Shravani Sadawarte.
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 for detecting artificial intelligence generated voice in audio recordings is disclosed. The system comprises a processor coupled to memory storing programmed instructions. An audio input module receives and standardizes audio files. A noise reduction module preprocesses audio using spectral gating algorithms. A feature extraction module computes mel-frequency cepstral coefficients, spectral centroid, zero crossing rate, spectral bandwidth, and chroma features. A machine learning classification module processes features through a trained ensemble classifier outputting a probability score. A speech-to-text conversion module transcribes audio content. A keyword detection module identifies scam-related keywords in transcripts. A risk assessment module computes a unified risk score combining the probability score and keyword detection results through weighted aggregation. The system achieves enhanced detection accuracy exceeding 94 percent through hybrid acoustic and linguistic analysis while maintaining computational efficiency suitable for standard computing hardware."
Disclaimer: Curated by HT Syndication.
