MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202641001506 A) filed by Btp Madhav; and Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, on Jan. 6, for 'effective f0 extraction method using sff-based saliency analysis for high noise scenarios.'
Inventor(s) include Chakilam Mani Kumar; Botsa Kishore Kumar; Paidi Gangamohan; Nuthi Ritishree; and B T P Madhav.
The application for the patent was published on Jan. 23, under issue no. 04/2026.
According to the abstract released by the Intellectual Property India: "Fundamental frequency (F0) plays a crucial role in speech processing. Estimating F0 in high-noise scenarios is the most challenging task. To address this issue, a method for extracting F0 using the Single Frequency Filtering (SFF) technique and saliency plot is proposed. The proposed SFF-based saliency analysis F0 extraction method demonstrates improved performance for clean speech and speech across various noise levels, with a low Gross Pitch Error (GPE) rate, as evaluated on the CMU Arctic database. This invented method can also be utilised for F0 extraction in clean speech, noisy speech, emotional speech, and pathological speech."
Disclaimer: Curated by HT Syndication.
