Neural network howling suppression method and system for digital hearing aid and storage medium

A neural network and hearing aid technology, applied in hearing aids, sensors, transducer circuits, etc., can solve the problems of lack of howling suppression speed and intensity, secondary damage to the patient's auditory system, and poor hearing aid wearing experience, and achieve the suppression effect. Good, reduce the chance of recurrence, prevent the effect of recurrence

Inactive Publication Date: 2019-05-21
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the structural defect of the ear-hook hearing aid makes it particularly prone to howling, which makes the wearing experience of the hearing aid wearer poor, and the sudden howling may even cause secondary damage to the patient's aud

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
  • Neural network howling suppression method and system for digital hearing aid and storage medium
  • Neural network howling suppression method and system for digital hearing aid and storage medium
  • Neural network howling suppression method and system for digital hearing aid and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] A neural network howling suppression method for digital hearing aids of the present invention uses a neural network to detect howling in each frame of speech in real time, and realizes a binary classification problem, that is, when there is a howling in the current frame, the network output is 1. When there is no howling, the output of the network is 0; for the speech frame with howling, it is necessary to adopt the strategy of buffer suppression to suppress the howling, so that the howling is suppressed during the formation process, so that it will not develop into a piercing scream The algorithm block diagram of the whole set of howling detection and suppression is as follows: figure 1 shown.

[0028] figure 1 It is the overall block diagram of the neural network howling suppression algorithm, which is mainly composed of two modules: howling detection module and buffer suppression module. The howling detection module integrates a well-trained neural network model to...

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 neural network howling suppression method for a digital hearing aid, and the method sequentially comprises the following steps: a preprocessing step: receiving a voice signal,carrying out the sampling and framing of the voice signal, and transmitting the voice signal to a howling detection module; A howling detection step: receiving the voice frame by a howling detectionmodule, detecting whether the voice frame is the howling frame by the howling detection module, if the voice frame is not the howling frame, enabling the voice signal to directly pass through, and continuing the subsequent processing; If the frame is the howling frame, entering a buffer inhibition module; And a buffer suppression step: suppressing the howling frame by a buffer suppression module.The method has the beneficial effects that 1, howling frames can be tracked and suppressed in real time, the suppression effect is better, and the algorithm operation complexity is not high; 2, the neural network is adopted for howling detection, so that the accuracy is higher, and the loss of normal voice is smaller; And 3, a buffer inhibition strategy can prevent howling from recurring in a short time, so that the howling recurrence probability is reduced.

Description

technical field [0001] The invention relates to the field of software technology, in particular to a neural network howling suppression method, system and storage medium for digital hearing aids. Background technique [0002] At present, hearing aid products on the market are mainly divided into three categories: cassette hearing aids, ear-hook hearing aids and ear canal hearing aids. Among them, the most widely used and the best market prospect is the ear-hook hearing aid. Compared with the other two types of hearing aids, it is more convenient to carry, can be used at any time, and has better performance. However, the structural defects of the ear-hook hearing aid make it particularly prone to howling, which makes the wearing experience of the hearing aid wearer poor, and the sudden howling may even cause secondary damage to the patient's auditory system. Although some high-performance digital hearing aids on the market are already equipped with howling suppression functi...

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): H04R3/00H04R25/00
CPCH04R3/00H04R3/02H04R25/00
Inventor 张禄王明江张啟权孙凤娇轩晓光张馨
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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