公开(公告)号：US20250069593A1

公开(公告)日：2025-02-27

申请号：US18454045

申请日：2023-08-22

Applicant: Google LLC

Inventor： Vikram Aggarwal ,  Ambarish Jash ,  Sukhdeep Singh Sodhi

IPC: G10L15/16 ,  G06F16/2457 ,  G06F16/638 ,  G10L15/02 ,  G10L15/06 ,  G10L15/22

Abstract: A method includes obtaining, from a user device associated with a user, an audio signature, the audio signature extracted from audio data corresponding to a query spoken by the user. The method also includes processing, using a neural network, the audio signature to identify document tokens that match the audio signature within a shared embedding space, the neural network trained to jointly embed audio signatures and document tokens in the shared embedding space. The method also includes retrieving, using the document tokens and the shared embedding space, a set of search results for the query, and providing, for output from the user device, one or more search results from the set of search results to the user.