公开(公告)号：US20250149019A1

公开(公告)日：2025-05-08

申请号：US19020264

申请日：2025-01-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Sadekov TASNIMA ,  Vadim POPOV ,  Gogoryan VLADIMIR ,  Kudinov MIKHAIL

IPC: G10L13/02 ,  G10L21/12 ,  G10L25/30

Abstract: Embodiments of the present application provide a method for speech generation and a related device, the method includes: obtaining a first source data input to a speech generation model including multiple encoders and a decoder, where types of input data of the multiple encoders are different; generating a first acoustic feature by a first encoder among the multiple encoders based on the first source data; and converting a second acoustic feature determined from the first acoustic feature into a third acoustic feature by the decoder. The above technical solution can rely on a single model to perform different speech generation tasks.