公开(公告)号：US11450310B2

公开(公告)日：2022-09-20

申请号：US16989012

申请日：2020-08-10

Applicant: ADOBE INC.

Inventor： Nikita Kapoor ,  Jaya Dodeja ,  Nikaash Puri

IPC: G10L15/06 ,  G10L19/04 ,  G10L15/02 ,  G10L15/18 ,  G10L15/16 ,  G10L25/51

Abstract: Systems and methods for spoken language understanding are described. Embodiments of the systems and methods receive audio data for a spoken language expression, encode the audio data using a multi-stage encoder comprising a basic encoder and a sequential encoder, wherein the basic encoder is trained to generate character features during a first training phase and the sequential encoder is trained to generate token features during a second training phase, and decode the token features to generate semantic information representing the spoken language expression.