MUMBAI, India, March 14 -- Intellectual Property India has published a patent application (202617013938 A) filed by Google Llc, Mountain View, U.S.A., on Feb. 9, for 'zero-shot task expansion of asr models using task vectors.'
Inventor(s) include Audhkhasi, Kartik; Ramesh, Gowtham; and Ramabhadran, Bhuvana.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "A method (400) includes training, using an un-supervised learning technique (600), an auxiliary ASR model (200) based on a first set of un-transcribed source task speech utterances (106) to determine a first task vector, training, using the un-supervised learning technique, the auxiliary ASR model based on a second set of un-transcribed speech utterances to determine a second task vector, and training, using the un-supervised learning technique, the auxiliary ASR model based on un-transcribed target task speech utterances to determine a target task vector. The method also includes determining a first correlation between the first and target task vectors, determining a second correlation between the second and target task vectors, and adapting parameters of a trained primary ASR model based on the first and second source task vectors and the first and second correlations to teach the primary ASR model to learn how to recognize speech associated with the target task."
The patent application was internationally filed on Aug. 27, 2024, under International application No.PCT/US2024/044082.
Disclaimer: Curated by HT Syndication.
