公开(公告)号：US20210280202A1

公开(公告)日：2021-09-09

申请号：US17330126

申请日：2021-05-25

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xilei WANG ,  Wersfu WANG ,  Tao SUN

IPC: G10L21/013 ,  G10L13/033 ,  G10L15/02 ,  G10L25/30 ,  G06N3/08

Abstract: The disclosure provides a voice conversion method, a voice conversion apparatus, an electronic device, and a storage medium, related to the field of voice conversion, speech interaction, natural language processing, and deep learning. The method includes: acquiring a source speech of a first user and a reference speech of a second user; extracting first speech content information and a first acoustic feature from the source speech; extracting a second acoustic feature from the reference speech; acquiring a reconstructed third acoustic feature by inputting the first speech content information, the first acoustic feature, and the second acoustic feature into a pre-trained voice conversion model, in which the pre-trained voice conversion model is acquired by training based on speeches of a third user; and synthesizing a target speech based on the third acoustic feature.

公开(公告)号：US20210201887A1

公开(公告)日：2021-07-01

申请号：US17205121

申请日：2021-03-18

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

Inventor： Zhijie CHEN ,  Tao SUN ,  Lei JIA

IPC: G10L13/047 ,  G10L25/18 ,  G10L25/30

Abstract: The present application discloses a method and an apparatus for training a speech spectrum generation model, as well as an electronic device, and relates to the technical field of speech synthesis and deep learning. A specific implementation is as follows: inputting a first text sequence into the speech spectrum generation model to generate an analog spectrum sequence corresponding to the first text sequence, and obtain a first loss value of the analog spectrum sequence according to a preset loss function; inputting the analog spectrum sequence corresponding to the first text sequence into an adversarial loss function model, which is a generative adversarial network model, to obtain a second loss value of the analog spectrum sequence; and training the speech spectrum generation model based on the first loss value and the second loss value.

公开(公告)号：US20210390943A1

公开(公告)日：2021-12-16

申请号：US17111238

申请日：2020-12-03

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Zhengkun GAO ,  Junteng ZHANG ,  Wenfu WANG ,  Tao SUN

IPC: G10L13/047 ,  G10L13/10 ,  G10L13/06

Abstract: The present disclosure discloses a method and apparatus for training a model, a method and apparatus for synthesizing a speech, a device and a storage medium, and relates to the field of natural language processing and deep learning technology. The method for training a model may include: determining a phoneme feature and a prosodic word boundary feature of sample text data; inserting a pause character into the phoneme feature according to the prosodic word boundary feature to obtain a combined feature of the sample text data; and training an initial speech synthesis model according to the combined feature of the sample text data, to obtain a target speech synthesis model.