Method for achieving self-adaptive switching of male voice and female voice
An adaptive, male-female technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of not being able to automatically change the voice change target, and not being able to monitor the speaker's gender in real time, so as to achieve accurate dynamic judgment, accurate judgment, and reduce misjudgment rate effect
Inactive Publication Date: 2014-01-15
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 16 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing voice change methods need to manually set the voice change target (such as setting male to female, or female to male). Umlaut
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
[0038] Such as figure 1 As shown, the self-adaptive implementation method for male and female voice switching in this embodiment includes the following steps:
[0039] (1) Training process:
[0040] (1-1) Collection of voice databases: 10 groups of male and female voice databases were extracted mainly from the electronic Chinese dictionary human pronunciation database according to words, including 5 groups of boys and 5 groups of girls. Each group of databases contains the pronunciation of 3893 commonly used words ;
[0041] (1-2) Perform deaverage energy preprocessing on the speech data in the speech database;
[0042] First intercept the data of the speech start point and the end point, first count the average energy of the whole speech, in order to simplify the calculation, the present invention takes the average value of the absolute value of each speech data as its average energy The first speech signal value is greater than That is, the starting point of the speech...
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
The invention discloses a method for achieving self-adaptive switching of a male voice and a female voice. The method comprises the steps that when training is conducted, voice data of a voice database are sectioned, voice data of a voice frequency database are extracted, the dynamic and static Meyer cepstrum characteristics of the voice data are extracted, and then the voice data are transmitted to a depth limitation Bohr machine network for voice gender study. When a user uses the voice frequency database, voice signals are collected, the voice signals are processed according to the steps the same as the voice data of the voice database and are transmitted to the depth limitation Bohr machine network and the voice gender is judged; according to the result of the judgment of the voice gender, the inflexion target is set, the time dynamic programming SOLAFS algorithm is used for regulating the duration of the voice signals and sampling the duration of the voice signals again according to the inflexion target, and finally the effect of switching the male voice and female voice automatically is achieved. The method for achieving the self-adaptive switching method of the male voice and the female voice switching method can distinguish the gender in real time and set the inflexion target in a self-adaptive mode and then carry out the real-time inflexion processing, parameters do not need to be set manually when the method is used every time, and the dynamic judgment of the voice is accurate.
Description
technical field [0001] The invention relates to the fields of machine learning and audio processing, in particular to a method for adaptively realizing the switching between male and female voices. Background technique [0002] The mutual conversion of male and female voices is achieved by changing the pitch and timbre of voice signals. The traditional method is to use voice signal processing methods, which is an important theoretical research direction in the field of voice signal processing, and male and female voice switching can be applied in secure communication, entertainment It has good practical application value in communication and other fields. There are also many methods to design the male and female voice switching method at present, as current patent CN03137014.4 provides a kind of voice changing method, this method reaches the effect of voice changing by manually setting the voice changing target, by changing the length of the signal. Patent CN200410062337.1 ...
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 Applications(China)
IPC IPC(8): G10L21/003G10L15/02
Inventor 郭礼华邓迪
Owner SOUTH CHINA UNIV OF TECH