Prosodic structure forming method based on prosodic phrase

A technology of prosody and phrases, applied in the field of multi-layer prosody structure generation, which can solve the problems of restricting the selection of features and not being able to consider features

Inactive Publication Date: 2010-02-17
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the independence assumption of its output, HMM cannot conside

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
  • Prosodic structure forming method based on prosodic phrase
  • Prosodic structure forming method based on prosodic phrase
  • Prosodic structure forming method based on prosodic phrase

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The prosodic structure generation method based on prosodic phrases proposed by the present invention includes three parts: prosodic phrase boundary prediction, prosodic word boundary prediction and rule correction, and a three-layer prosodic structure generation system based on prosodic phrases is constructed. On the basis of word segmentation boundary and part-of-speech tagging, prosodic phrase boundary information is given first, and then prosodic word boundary information is further given on the basis of word segmentation boundary, part-of-speech tagging and prosodic phrase boundary information. In the judgment of the above two types of boundaries, the system first uses the maximum entropy model to make judgments, and then uses the error-driven rule learning method for machine learning to generate a certain number of optimal rules for some errors in the results, and further refines the results. Optimization. Finally, in the third stage, the prosodic structure boundar...

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 provides a novel prosodic structure boundary division forming method based on prosodic phrases. The method combines machine learning with rules to greatly improve the accuracy of the prediction of Chinese text prosodic structure boundary. Prosodic phrase boundaries are firstly identified on the premise that input files goes through word segmentation and part of speech tagging, then prosodic word boundaries are formed by combining prosodic phrase boundary information, and finally a plurality rules are artificially added to carry out integral modification. In prosodic phrase and prosodic word boundary identification, characteristics are respectively designed and selected for establishing a characteristic template, and a prosodic phrase model and a prosodic word model are established by utilizing the maximum entropy algorithm for respectively identifying prosodic boundaries of two stages. In addition, aiming at the errors in identification of a maximum entropy model, an optimal rule is selected by utilizing an error-driven rule learning method to further improve the accuracy. Based on the method, the prosodic structure boundary division forming method based on prosodic phrases is provided, and the method can effectively improve the accuracy of prosodic structure prediction and the naturalness of speed synthesis.

Description

technical field [0001] The invention belongs to the field of computer man-machine communication, and designs a multi-layer prosodic structure generation method based on prosodic phrases. In the prediction of prosodic boundary structure, the present invention introduces a machine learning method, and performs hierarchical processing on prosodic phrases and prosodic words. On the premise of systematic analysis and induction, the feature templates of prosodic phrases and prosodic words are designed in a targeted manner, and machine learning methods such as maximum entropy algorithm are used to design a system that can effectively and accurately generate prosodic boundary information. in practical applications such as speech synthesis. Background technique [0002] With the development of information technology, language technology and computer technology, speech synthesis technology has attracted more and more people's attention. By inputting text, the computer can speak huma...

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): G10L13/08G06N1/00G06F17/30
Inventor 董远周涛
Owner BEIJING UNIV OF POSTS & TELECOMM
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