Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A voice and pathological technology, applied in the field of pathological voice subdivision, can solve the problems of not making full use of advantages and not considering feature complementarity, etc.
Inactive Publication Date: 2013-08-21
SUZHOU UNIV
View PDF3 Cites 12 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
There are two problems in the current methods. One is that the precise subdivision of pathological voices is not carried out, and only the judgment of right and wrong is carried out; the other is that the advantages of each feature are not fully utilized, especially the complementarity between features is not considered. sex
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0041] see image 3 As shown, the recognition module includes the following steps:
[0042] Step 8) extracting the feature parameters in M of the input voice signal;
[0043] Step 9) Load the trained GMM matrix;
[0044] Step 10) Input the feature parameters extracted in step 8) into the trained GMM matrix to obtain the likelihood of each feature corresponding to each type of voice;
[0045] Step 11) According to the likelihood obtained in step 10), obtain the probability of each type of pathological voice;
[0046] Step 12) Vote for the pathological voice type corresponding to the highest probability, and each feature will have one vote;
[0047] Step 13) Combine all the features and count the votes; if it is the last model, the voice to be recognized is the pathological voice type corresponding to the largest total number of votes, and end; if it is not the last model, the total number of votes is greater than the set threshold, then The voice to be recognized is the t...
Embodiment 2
[0049] see Figure 4 As shown, the recognition module includes the following steps:
[0050] Step 8) extracting the feature parameters in M of the input voice signal;
[0051] Step 9) Load the trained GMM matrix;
[0052] Step 10) Input the feature parameters extracted in step 8) into the trained GMM matrix to obtain the likelihood of each feature corresponding to each type of voice;
[0053] Step 11) According to the likelihood obtained in step 10), obtain the probability that the voice is each type of pathological voice;
[0054] Step 12) The probability weighted summation corresponding to all features is used as the total matching Match;
[0055] Step 13) Select the largest Match among all pathological voice type matching Matches; if it is the last model, the voice to be recognized is the pathological voice type corresponding to the largest Match, and end; if not, the Match is greater than the set threshold, then The voice to be recognized is the type of pathological ...
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 pathological voice subdivision method. A model training module and an identification module are included. The model training module is used for modeling of input voice signals, getting corresponding likelihood, calculating and comparing matching probabilities, and finding out voice signals meeting the conditions. The identification module is used for matching the voice signals which meet the conditions. The lengths of the input voice signals are not required, the voice signals can have characteristic parameters of any types, and different weights are distributed to different characteristics. Therefore, advantages of all parameters can be utilized, and the number of dimensions of the characteristic parameters is not limited. Multiple times of trainings can be carried out, retraining is carried out on voice signals which are difficult to identify, and threshold values, finishing conditions and identification conditions can be flexibly set in the training. By means of the pathological voice subdivision method, types of pathological voices can be automatically set and subdivided precisely, pre-diagnosis of voice diseases and timely-tracking of recovery condition of a patient are achieved, and meanwhile the pathological voice subdivision method is suitable for being used for health self-inspection of teachers and singers and the like.
Description
technical field [0001] The invention belongs to the field of noise, and in particular relates to a pathological voice subdivision method. Background technique [0002] The investigation of the voice status shows that at least 100 million people in our country suffer from various voice diseases, which are related to many reasons such as physiology and working environment. Vocal speech dysfunction is mainly caused by functional or organic damage to the vocal speech organs. In the early days, the detection of pathological voice was mainly based on the subjective judgment of medical experts, and the misjudgment rate was relatively high. The disadvantage of the electronic instrument diagnosis method is that it is difficult for the naked eye to capture the moment of pronunciation, and it will cause inconvenience to the patient, resulting in inaccurate diagnosis results. With the introduction of pattern recognition, the convenient and non-invasive automatic detection method has ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more