Method for recognizing voiceprint of Parkinson patients based on WMFCC (Weighted Mel-Frequency Cepstral Coefficient) and DNN

A voiceprint recognition and patient technology, applied in speech analysis, instruments, etc., can solve the problems of small high-order cepstral coefficients and prominent MFCC parameter sensitivity

Pending Publication Date: 2019-01-29
SHANGHAI MARITIME UNIVERSITY
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1. Use WMFCC (weighted MFCC) to extract voiceprint features, solve the problem of ve

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
  • Method for recognizing voiceprint of Parkinson patients based on WMFCC (Weighted Mel-Frequency Cepstral Coefficient) and DNN
  • Method for recognizing voiceprint of Parkinson patients based on WMFCC (Weighted Mel-Frequency Cepstral Coefficient) and DNN
  • Method for recognizing voiceprint of Parkinson patients based on WMFCC (Weighted Mel-Frequency Cepstral Coefficient) and DNN

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0011] Step 1: WMFCC voiceprint feature extraction

[0012] The extraction of speech feature parameters is crucial in voiceprint recognition. At present, in the field of voiceprint recognition, the most commonly used feature extraction is MFCC. The voice signal changes slowly. When it is sensed in a short period of time, the voice signal is generally considered stable in a time interval of 10-30ms. Therefore, it should be calculated by short-time spectrum analysis, and the Mel scale should be used to estimate the frequency perception of the human ear, which is calculated in a way that 1000Hz corresponds to 1000Mel.

[0013] This technology uses temporal speech quality, frequency spectrum, and cepstrum domain in order to develop a more objective assessment to detect speech disorders. These measurements include the fundamental frequency of vocal cord vibration, absolute sound pressure level, jitter, low light and harmonics. Based on the pronunciation characteristics of PD patients...

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 provides a method for recognizing the voiceprint of Parkinson patients based on the WMFCC (Weighted Mel-Frequency Cepstral Coefficient) and DNN, which is used for distinguishing the Parkinson patients from healthy people. The WMFCC solves the problems such as small high-order cepstral coefficient and poor representation ability of feature components to audio through calculating the weighted sum coefficient of the cepstral coefficients in the patient voiceprint. The DNN carries out training, classification and recognition so as to effectively improve the accuracy of the system, and the calculation amount of a loss function is reduced by using an MBGD optimization algorithm so as to improve the training speed of the system. Samples in a PD (Parkinson database) are used for training and classification testing, thereby improving the accuracy of identifying the Parkinson patients, and providing a good solution for early rapid auxiliary diagnosis for the Parkinson patients.

Description

Technical field: [0001] The present invention relates to the feature extraction and discriminant classification of voiceprints of Parkinson's patients and healthy people, specifically, it is a voiceprint recognition method for Parkinson's patients based on WMFCC and DNN, which provides a good solution for early and rapid auxiliary diagnosis of PD patients plan. Background technique: [0002] Parkinson's disease (PD) is the second most common neurological disorder after Alzheimer's disease. Voice disturbance is considered one of the earliest signs of disease. In the early stages, subtle abnormalities in the sound are imperceptible to the listener, but can be objectively assessed by acoustic analysis of the recorded speech signal. Existing PD detection uses PET-CT imaging equipment to detect whether dopaminergic neurons are reduced, but its high price and radioactivity make it less acceptable to patients. In the 1990s, various shallow machine learning models were proposed o...

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): G10L17/00G10L17/04G10L25/24
CPCG10L17/04G10L25/24G10L17/00
Inventor 张颖徐志京
Owner SHANGHAI MARITIME UNIVERSITY
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