Rhythm predicting method and system

A prediction method and prosody technology, applied in speech synthesis, speech analysis, instruments, etc., can solve the problems of time-consuming and high labor costs, and achieve accurate results

Active Publication Date: 2017-08-11
IFLYTEK CO LTD
View PDF14 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a prosody prediction method and system to solve the problem of manually marking the prosody boundaries of all training text data to train the text prosody model when building the model in the prior art, resulting in high labor cost and long time-consuming question

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
  • Rhythm predicting method and system
  • Rhythm predicting method and system
  • Rhythm predicting method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the existing prosody prediction methods are briefly introduced first. Existing technologies usually construct text prosody models through supervised methods, predict the prosody of text data, and obtain prosody prediction results, such as figure 1 shown, including:

[0070] First, the text prosody model is constructed by a supervised method. The supervised method constructs the text prosody model, that is, the training data used for training the text prosody model must be completely pre-labeled manually, and the labeling results are given, such as manually training The prosodic boundary of the data is marked, and the model construction method can be as follows: collect a large amount of text data, and manually mark the prosodic boundary of the text data, and use the manual labeling result as the labeling feature of the text data, that is, the curre...

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 rhythm predicting method and a system wherein the method comprises: creating a text rhythm model in advance; gathering text data with corresponding voice data; based on the rhythm information of the voice data, performing automatic rhythm marking to the corresponding text data; obtaining the automatically marked text data; using the automatically marked text data to train the text rhythm model; receiving the to-be-predicted text data; then, extracting the text characteristics of the to-be-predicted text data; and finally utilizing the text characteristics and the text rhythm model to perform rhythm predictions to the to-be-predicted text data. According to the method and the system, as the gathered text data all correspond to voice data and the voice data contain the rhythm information in reality, it is possible to perform automatic rhythm marking to the text data. Therefore, with the system and the method, the problem in the prior art can be solved that artificial marking is required for the rhythm edges of all trained text data to train the text rhythm model, which leads to the high human cost and the long consumption of time.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a prosody prediction method and system. Background technique [0002] Speech synthesis is an important part of language information processing. It refers to the process of outputting speech after a certain conversion of the text, and trying to make the synthesized speech have good naturalness and intelligibility. Prosodic prediction is mainly aimed at the prediction of prosodic phrases in text data, and predicts the corresponding prosodic boundary positions in text data. The prosody prediction method is generally used in the front-end text processing of speech synthesis. After predicting the prosodic boundary position, the corresponding pause can be given according to the corresponding prosodic boundary position during speech synthesis, thereby improving the naturalness of the synthesis; in addition, it can also be used for natural language It is understood that differ...

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): G10L13/10
CPCG10L13/10G10L2013/105
Inventor 周明江源胡国平胡郁刘庆峰
Owner IFLYTEK CO LTD
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