Method and device for training voice synthesis model, electronic equipment and storage medium
A speech synthesis and model training technology, applied in speech synthesis, speech analysis, speech recognition, etc., can solve the problems of high R&D cost, high cost, and long R&D cycle of speech synthesis technology, and achieve the goal of shortening R&D cycle and reducing R&D cost Effect
Active Publication Date: 2019-08-16
GUANGZHOU DUOYI NETWORK TECH +2
View PDF3 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the acquisition period of high-quality corpus is long and the cost is high. Using the model training scheme in the existing technology will lead to the problems of long research and development period and high research and development cost of speech synthesis technology.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0049] The embodiment of the present invention provides a speech synthesis model training method, please refer to figure 1 , which is a flowchart of a preferred embodiment of a speech synthesis model training method provided by the present invention; specifically, the speech synthesis model training method includes:
[0050] S1. Construct the original speech synthesis model based on the deep learning method;
[0051] S2. Obtain a pre-built basic text-to-speech par...
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
Login to View More Abstract
The invention discloses a method and device for training a voice synthesis model, electronic equipment and a storage medium. The method comprises the steps that an original voice synthesis model basedon a deep learning method is constructed; a pre-constructed basic text voice parallel corpus is acquired, and the original voice synthesis model is trained according to the basic text voice parallelcorpus to obtain a basic voice synthesis model; a pre-generated target text voice parallel corpus is acquired, and the basic voice synthesis model is trained according to the target text voice parallel corpus to obtain the target voice synthesis model, wherein the target text voice parallel corpus meets the preset voice synthesis requirement. According to the method and device for training the voice synthesis model, the electronic equipment and the storage medium, the target voice synthesis model can be trained through the small-scale target text voice parallel corpus, the development period of the voice synthesis technology is effectively shortened, and the development cost is reduced.
Description
technical field [0001] The invention relates to the technical field of speech synthesis, in particular to a speech synthesis model training method, device, electronic equipment and storage medium. Background technique [0002] Speech synthesis technology is a technology used to convert text information into voice information. Currently, the widely used speech synthesis technologies include parametric synthesis-based speech synthesis technology and deep learning-based speech synthesis technology. [0003] In speech synthesis technology based on parametric synthesis, when performing speech synthesis, the text is abstracted into phonetic features, and speech parameters are generated according to a statistical model. After predicting the acoustic features, the speech output is synthesized by a vocoder. The statistical model learning the corresponding relationship between phonetic features and acoustic features also needs to be trained through a large number of high-quality corp...
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
Login to View More IPC IPC(8): G10L13/047G10L15/26
CPCG10L13/047G10L15/26
Inventor 徐波
Owner GUANGZHOU DUOYI NETWORK TECH