LSTM-based method for inverse interpretation of independent speaker speech pronunciation

An independent speaker and voice technology, applied in the field of test systems, can solve problems such as inability to practically apply, there are deviations, and the feature selection effect is not good enough, so as to achieve the effect of improving RMSE and correlation coefficient and overcoming discontinuity.

Active Publication Date: 2019-02-15
SUN YAT SEN UNIV
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is not only time-consuming to collect, but also cannot be practically applied
[0005] Second, the feature selection effect is not good enough, the root mean square error (Root mean-squared error, RMSE) is about 2-5mm and the correlation coefficient r is about 0.7, and it is predicting

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
  • LSTM-based method for inverse interpretation of independent speaker speech pronunciation
  • LSTM-based method for inverse interpretation of independent speaker speech pronunciation
  • LSTM-based method for inverse interpretation of independent speaker speech pronunciation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] like Figures 1 to 7 Shown is a kind of embodiment of the method for the inverse solution of independent speaker voice pronunciation based on LSTM of the present invention, concrete steps are as follows:

[0045] (1) Firstly, collect audio signals and synchronous track signals of 4 designated individuals, and measure upper lip (Upper lip, UL), lower lip (Lower lip, LL), lower gingiva (Lower incisor, LI), tongue tip ( Tonguetip, TP), tongue (Tongue body, TB), tongue base (Tongue dorsum, TD) six points of data collection;

[0046] (2) After step (1), select the bridge of the nose (RF) as a reference point, and place sensors at the reference point for data collection;

[0047] (3) After step (2), select three of them as A, B, and C as trainers, and D as testers;

[0048] (4) Perform feature extraction on the speech signal of the training person, extract the Mel Frequency Cepstrum Coefficient (MFCC) and phoneme posterior probability (phoneme posterior probabilities, PPP);...

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 the test system and a method thereof and particularly relates to an LSTM-based method for inverse interpretation of independent speaker speech pronunciation. The method is specifically characterized in that (1), firstly, four designated audio signals and synchronized trajectory signals are collected, and data at six points of an upper lip (UL), a lower lip (LL), a lower incisor (LI), a tongue tip (TP), a tongue body (TB), a tongue dorsum (TD) are collected through mounting a sensor; and (2), after the step (1), a nose bridge (RF) is selected as a reference point, and asensor is further placed at the reference point for data collection. The method is advantaged in that firstly, the speech pronunciation trajectory of speakers not appearing in a training set is predicted; secondly, input characteristics are changed, better and more appropriate acoustic characteristics are selected as network input, and RMSE and correlation coefficients are improved; and thirdly,discontinuous and unsmooth characteristics of trajectory collection are overcome.

Description

technical field [0001] The present invention relates to a test system and a method thereof, more specifically to a method for inversely solving independent speaker voice pronunciation based on LSTM. Background technique [0002] The inverse solution of speech pronunciation is to obtain the quasi-solution model by collecting the trajectory data of the pronunciation organs and synchronous audio, and training the neural network model, trying to infer the position of the vocal tract pronunciation device from the sound speech signal. The system is able to predict the position of the vocalizer from the acoustic signal. The system can be applied in the following aspects: in speech recognition, pronunciation information can improve the performance of the recognition system; in speech synthesis, it can improve the quality of speech and modify the characteristics of synthesized speech; in character animation, it can be used to automate movies or videos Facial animation for virtual ch...

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): G10L25/24G10L15/06G10L25/30G10L17/04
CPCG10L15/063G10L17/04G10L25/24G10L25/30
Inventor 覃晓逸张东李明
Owner SUN YAT SEN UNIV
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