公开(公告)号：US20240203404A1

公开(公告)日：2024-06-20

申请号：US18081569

申请日：2022-12-14

Applicant: GOOGLE LLC

Inventor： Nir Shabat ,  Volodymyr Polosukhin ,  Shlomo Fruchter ,  Golan Pundak ,  Roy Atsmon

IPC: G10L15/18 ,  G10L13/027 ,  G10L15/26

CPC classification number: G10L15/1815 ,  G10L13/027 ,  G10L15/26

Abstract: In various implementations, a method implemented by one or more processors of a computing device can comprise receiving audio data that captures a spoken utterance of a user; processing the audio data using an automatic speech recognition (ASR) model to generate textual data corresponding to the spoken utterance; generating a semantic representation corresponding to the spoken utterance of the user based on applying both the audio data and the textual data as input across a large language model (LLM); and causing the semantic representation corresponding to the spoken utterance of the user to be utilized in fulfilling the spoken utterance.