Prosody model training method and device thereof

A model training and prosody technology, applied in the field of neural network, can solve the problems of prosodic word prosodic phrase prediction error, reduce prosodic word boundary, prosodic phrase boundary prediction accuracy, etc.

Active Publication Date: 2020-06-09
BEIJING UNISOUND INFORMATION TECH +1
View PDF13 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, in order to predict the boundaries of prosodic words and prosodic phrases, a pre-set prosodic model is usually used for prediction, and this prosodic model is relatively fixed, so it will lead to errors in the prediction of the boundaries of prosodic words and prosodic phrases , thereby reducing the prediction accuracy of prosodic word boundaries and prosodic phrase boundaries

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
  • Prosody model training method and device thereof
  • Prosody model training method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.

[0049] At present, in order to predict the boundaries of prosodic words and prosodic phrases, a pre-set prosodic model is usually used for prediction, and this prosodic model is relatively fixed, so it will lead to errors in the prediction of the boundaries of prosodic words and prosodic phrases , thus reducing the prediction accuracy of prosodic word boundaries and prosodic phrase boundaries. ...

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 relates to a prosody model training method and a device thereof. The method comprises the following steps: receiving a training corpus containing prosodic annotation information; inputting the training corpus into a prosody model to be trained to obtain a prosody output result; and training network parameters of the prosody model to be trained according to the prosody output result and/or the prosodic annotation information to obtain a target prosody model. Through the technical scheme of the invention, the target prosody model is a personalized prosody model with relatively highadaptability and precision, and the annotation universality can be better learned from training data from different sources, so that the prediction accuracy of prosodic word boundaries and prosodic phrase boundaries and the robustness of the prosody model can be improved.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a prosody model training method and device. Background technique [0002] At present, in order to predict the boundaries of prosodic words and prosodic phrases, a pre-set prosodic model is usually used for prediction, and this prosodic model is relatively fixed, so it will lead to errors in the prediction of the boundaries of prosodic words and prosodic phrases , thus reducing the prediction accuracy of prosodic word boundaries and prosodic phrase boundaries. Contents of the invention [0003] Embodiments of the present invention provide a prosodic model training method and device. Described technical scheme is as follows: [0004] According to the first aspect of the embodiments of the present invention, a prosodic model training method is provided, including: [0005] receiving training corpus containing prosodic labeling information; [0006] The training corpus ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L13/10G10L25/30G06N3/04G06N3/08
CPCG10L13/10G10L25/30G06N3/08G06N3/045
Inventor 吴朗
Owner BEIJING UNISOUND INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap