Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech synthesis method, speech synthesis model training method, related device, equipment and medium

A technology of speech synthesis and training methods, applied in speech synthesis, speech analysis, instruments, etc., can solve the problems of large data volume, uncontrollable rhythm, slow convergence, etc., achieve high stability and robustness, speed up convergence, and small Bulk Data Friendly Effects

Pending Publication Date: 2022-03-18
GUANGZHOU HUYA TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Usually, the rhythm information can be digitally synthesized into the input of the speech synthesis model according to the resolution of the frame, but it requires a large amount of data and the convergence is relatively slow. The rhythm of the volume is uncontrollable

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Speech synthesis method, speech synthesis model training method, related device, equipment and medium
  • Speech synthesis method, speech synthesis model training method, related device, equipment and medium
  • Speech synthesis method, speech synthesis model training method, related device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The solutions of the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings.

[0026] In the following description, for purposes of illustration rather than limitation, specific details, such as specific system architectures, interfaces, and techniques, are set forth in order to provide a thorough understanding of the present application.

[0027] The terms "system" and "network" are often used interchangeably herein. The term "and / or" in this article is just an association relationship describing associated objects. There can be three relationships, for example, A and / or B, which can be: A exists alone, A and B exist simultaneously, and B exists alone. three situations. In addition, the character " / " in this article generally has an "or" relationship between context and context objects. In addition, "more" in this article is two or more than two.

[0028] see figure 1 , figure 1 It is a schematic flow...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a speech synthesis method, a speech synthesis model training method, a related device, equipment and a medium. The speech synthesis model training method comprises the following steps: acquiring a sample audio, and acquiring feature information of the sample audio; obtaining a sample Mel spectrum of the sample audio through a phoneme duration prediction model, obtaining sample phoneme weight information of the sample audio, and obtaining a sample phoneme duration; inputting the feature information of the sample audio, the sample Mel spectrum and the sample phoneme duration into the speech synthesis model to obtain sample synthesis speech and predicted phoneme weight information; and adjusting network parameters of the speech synthesis model based on the difference between the sample phoneme weight information and the predicted phoneme weight information. According to the scheme, very accurate phoneme duration information can be learned so as to accelerate convergence of the model, and the rhythm of speech synthesis can be efficiently controlled.

Description

technical field [0001] The present application relates to the technical field of speech synthesis, in particular to a speech synthesis method and its model training method, related devices, equipment and media. Background technique [0002] With the continuous development of electronic information processing technology, voice, as an important carrier for people to obtain information, has been widely used in daily life and work. In the application scenarios involving voice, the processing of speech synthesis is usually included. The speech synthesis refers to synthesizing the specified text or audio into target audio that meets the requirements. [0003] Take singing voice synthesis as an example. Singing voice synthesis is an important branch of speech synthesis. Singing voice synthesis has high requirements for rhythm and is difficult to learn. In addition, because singing voice synthesis requires more professional recorders (with a certain foundation in vocal music theory)...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L13/033G10L25/03G10L25/27
CPCG10L13/033G10L25/03G10L25/27
Inventor 周阳
Owner GUANGZHOU HUYA TECH CO LTD