An interactive self-fitting method for an intelligent hearing aid

Abstract

The invention discloses an interactive self-fitting method for an intelligent hearing aid, which comprises the following steps: step 1, the hearing-impaired patient listens to the test voice sent by the hearing aid and performs five-level evaluation, and forms an evaluation index for the sound quality of the hearing aid; step 2, according to the patient's 11-dimensional audiogram, 3-dimensional personality information, and voice evaluation form a feature sequence, and then calculate its similarity with the feature sequence in the fitting historical database Step 3, design a value function for parameter adjustment, and calculate the parameter adjustment strategy; the value of the strategy, Maximize the value of each parameter adjustment; step 4, construct the neural network, and obtain the weight of the neural network; step 5, input the test voice spectrum, voice evaluation, patient personality information and three consecutive sets of historical parameter adjustment strategies into the neural network, Regenerate test speech for evaluation by hearing-impaired patients. The present invention comprehensively considers the subjective and objective voice evaluation method, combines the deep learning network, integrates cognitive and personal factors into the hearing aid design, and has a good application prospect.

Description

technical field [0001] The invention relates to an interactive self-fitting technology for intelligent hearing aids, which belongs to the technical field of hearing aid fitting. Background technique [0002] Due to the degeneration of cognitive ability of hearing-impaired patients, the traditional method is inefficient, and the design concept of fitting by the patient has gradually become a research hotspot. Currently, the simplest self-fitting method is to let the user choose from a small number of pre-programmed algorithm configurations, which mainly depends on the optimization strategy of the pattern, that is, how well the preset matches the user population. [0003] Relevant studies have shown that more complex interactive self-fitting methods can better reflect the individual differences of patients. With the development of smartphones and earphones, the concept of self-fitting hearing aids has received more and more attention. The effectiveness of early hearing aids ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the problem that the traditional hearing aid fitting method relies heavily on hearing experts, and aims to establish an interactive self-fitting method for intelligent hearing aids, fully utilize the comprehensive information of patients, and improve fitting efficiency

Images