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

Voice time premeauring device and method based on decision tree

A prediction device and decision tree technology, applied in speech analysis, speech synthesis, instruments, etc., can solve the problems of different basic prediction units and unreasonable treatment

Inactive Publication Date: 2011-01-26
FUJITSU LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In the above analysis process, the biggest shortcoming is that when examining the impact of a certain contextual factor on the speech duration, different basic prediction units are often not treated differently
In fact, it is clearly unreasonable

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
  • Voice time premeauring device and method based on decision tree
  • Voice time premeauring device and method based on decision tree
  • Voice time premeauring device and method based on decision tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The specific implementation manner of the present invention will be described below in conjunction with the accompanying drawings.

[0044] 1. Definition of language and phonetic notation

[0045] The language and phonetics tagged sequence refers to the sequence obtained through the front-end language analysis and phonetics analysis of the speech synthesis system. Generally speaking, it corresponds to a text sentence. After being processed by the front-end of the speech synthesis system, it includes the following information: Chinese characters, word segmentation information, part-of-speech information, Chinese pinyin (syllable, semi-syllable) information, stress information, and prosodic boundary level information.

[0046] Definition 1: Prosodic boundary level information: indicates the pause level between syllables that needs to be given in the synthesized speech. Specifically, there are six levels: intra-word, inter-word, prosodic word boundary, prosodic phrase bo...

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

A device used for predicting voice time length based on decision tree consists of input unit for inputting mark sequence of language and voice, decision tree generating unit for decision tree to predict unit time length of voice, voice unit time length predicting unit for setting fixed time length and for setting variable quantity used to change unit fixed time length of voice, and output unit for outputting prediction result sequence of voice unit time length.

Description

technical field [0001] The invention relates to speech duration prediction technology of a speech synthesis system, in particular to a speech duration prediction device and method based on a decision tree. Background technique [0002] Speech duration is one of the most important prosodic features in human speech communication. On the one hand, the change of speech duration helps people to recognize the speech itself, and on the other hand, the change of rhythm assists people to divide a continuous speech flow into words and phrases, thus increasing the naturalness and intelligibility of speech. The quality of speech duration prediction directly affects the naturalness of the speech synthesis system. [0003] In human natural speech, the duration of speech is highly context-dependent. Many contextual factors such as: the phoneme itself, the surrounding phonemes, the prosodic boundary level around it, and whether it is stressed or not all have an important impact on the dur...

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 Patents(China)
IPC IPC(8): G10L13/08G10L13/00G10L19/04
Inventor 郭庆片江伸之
Owner FUJITSU LTD