公开(公告)号：US20230197096A1

公开(公告)日：2023-06-22

申请号：US17812784

申请日：2022-07-15

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Wenkai ZHANG ,  Ce ZHANG ,  Zheng LI ,  Lei JIA

IPC: G10L21/0224 ,  G10L15/22 ,  G10L25/30 ,  G10L15/06

CPC classification number: G10L21/0224 ,  G10L15/22 ,  G10L15/063 ,  G10L25/30 ,  G10L2015/223 ,  G10L2021/02082

Abstract: Provided are an audio signal processing method, a training method, an apparatus and a storage medium, relating to the field of data processing, in particular to, the field of voice. The audio signal processing method includes: eliminating at least part of a linear echo signal from a mixed voice signal, to obtain an intermediate processing signal, where the mixed voice signal is obtained by mixing a target voice signal with an echo signal, and the echo signal is generated in an environment where the target voice signal is located and includes the linear echo signal and a nonlinear echo signal; and removing the nonlinear echo signal and a residual part of the linear echo signal from the intermediate processing signal, by using a target full convolution neural network model, to obtain an approximate target voice signal, the target full convolution neural network model including at least two convolution layers.

公开(公告)号：US20250157457A1

公开(公告)日：2025-05-15

申请号：US19023572

申请日：2025-01-16

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Bin HUANG ,  Tao SUN ,  Ce ZHANG ,  Yongguo KANG ,  Xiaoyin FU ,  Lei JIA

IPC: G10L13/027

Abstract: A method of training a deep learning model and a method of synthesizing a speech are provided, which relate to a field of artificial intelligence technology, in particular to fields of large model, large language model, generative model, deep learning, and speech processing technologies. The method of training a deep learning model includes: determining a reference speech feature of a sample speech, the reference speech feature being associated with a prosodic feature of the sample speech; retrieving a speech library using a sample text corresponding to the sample speech, so as to obtain a pronunciation expression feature of the sample text; inputting the pronunciation expression feature into the deep learning model to obtain an output speech feature; determining a loss of the deep learning model according to the reference speech feature and the output speech feature; and adjusting a parameter of the deep learning model according to the loss.