Emotion voice creating method based on voice conversion
A speech conversion and speech technology, applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as difficulties in recording and labeling, and the analysis results are easily affected by emotional corpus.
Active Publication Date: 2011-02-02
中科极限元(杭州)智能科技股份有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] In order to solve the above-mentioned prior art that requires the support of a large-scale emotional speech library, recording and labeling such a large-scale speech library is a relatively difficult problem, and the analysis results are easily affected by the emotional corpus. The purpose of the present invention is based on the fundamental frequency target (pitch target) model sets up mapping relationship between neutrality and emotional fundamental frequency curve, and produces emotional voice by converting the form of fundamental frequency curve, for this reason, the present invention will provide a kind of use, calculation is relatively simple, easy to realize, training The process is automatic, and the analysis results are not easily affected by emotional corpus. Emotional voice generation method based on voice conversion
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] The present invention will be described in detail below with reference to the drawings. It should be noted that the described embodiments are only for illustrative purposes, rather than limiting the present invention.
[0024] According to the invention figure 1 The overall framework of emotional speech generation based on speech conversion is shown in the figure: The figure includes:
[0025] Speech analysis 12: is to analyze the neutral speech signal 11 to obtain the fundamental frequency curve 13 and the spectrum envelope 14.
[0026] Fundamental frequency conversion 15 based on the fundamental frequency target model: The usual fundamental frequency conversion method is to convert the fundamental frequency curve itself, while the present invention uses the fundamental frequency target model 15 to describe the fundamental frequency curve 13, and achieves this by converting the fundamental frequency target model parameters The purpose of converting the fundamental frequency ...
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
Login to View More Abstract
This invention discloses one new motion sound generation method based on sound conversion, which comprises the following steps: training phase and emotion sound extraction for spectrum and basic property to establish middle sound and emotion sound map relationship on frequency spectrum and basic spectrum frequency; extracting mode parameters from middle sound and emotion sound by use of Gauss mixture mode and sort regress tree method to establish aim module parameters functions; generation phase to extract frequency spectrum and basic frequency property for conversion on basic frequency curvewith emotion property; finally integrating the converted frequency spectrum and basic frequency curve with relative emotion conversion sound.
Description
Technical field [0001] The invention belongs to speech synthesis technology and relates to a new emotional speech generation method based on speech conversion. Background technique [0002] The technology of speech synthesis has been developed for decades and has made great progress in terms of both intelligibility and naturalness. However, although the current synthesized speech has no "machine flavor", it is still relatively boring. Nowadays, people can obtain a lot of information through the Internet. In applications such as e-shopping, online medical treatment, online chat, e-meeting, and voice e-mail, what people want to hear is no longer boring machine sounds, but more "Human touch" voice. If the synthesized speech has corresponding emotions, it will undoubtedly greatly enhance the humanization of the synthesized speech. Therefore, emotional speech synthesis is now a hot topic in the field of speech synthesis research. The research of emotional speech synthesis is a bran...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G10L13/00G10L13/08G10L13/02G10L21/00
Inventor 陶建华康永国
Owner 中科极限元(杭州)智能科技股份有限公司