Environmentally adaptive neural network noise reduction method and system for digital hearing aid and storage medium

Abstract

The invention provides an environmentally adaptive neural network noise reduction method for a digital hearing aid. The method comprises the following steps of receiving a voice signal with noise, sampling and framing the voice signal with noise, and then transmitting the voice signal with noise to an acoustic scene recognition module; conducting scene recognition, wherein an acoustic scene recognition module is adopted for recognizing the current acoustic scene, and then the acoustic scene recognition module autonomously selects different neural network models in a neural network noise reduction module for transmission; performing neural network noise reduction. The method has the advantages that the real-time performance of voice processing can be ensured, only forward propagation of a neural network is carried out, and the calculation amount is not high; the current acoustic scene can be recognized, then different neural network models are selected autonomously, targeted noise reduction processing is carried out on noise in different scenes, and higher voice quality and voice intelligibility can be ensured; instantaneous noise can be effectively suppressed.

Description

technical field [0001] The invention relates to the field of software technology, in particular to an environment adaptive neural network noise reduction method, system and storage medium for digital hearing aids. Background technique [0002] At present, high-performance digital hearing aids on the market have built-in noise reduction algorithms to eliminate background noise interference in the environment to meet the requirements of human hearing comfort. Due to the requirements of digital hearing aids for real-time speech processing, the noise reduction algorithms built into the hearing aids mostly use algorithms with low computational complexity such as spectral subtraction and Wiener filtering. These algorithms can only deal with simple and stable noise interference environments. The performance is poor in complex noise environments such as noise ratio and instantaneous noise, and the wearing experience of hearing loss patients is not good. Contents of the invention ...

AI Technical Summary

Problems solved by technology

Due to the requirements of digital hearing aids for real-time speech processing, the noise reduction algorithms built into the hearing aids mostly use algorithms with low computational complexity such as spectral subtraction and Wiener filtering. These algorithms can only deal with simple and stable noise interference environments. The performance is poor in complex noise environments such as noise ratio and instantaneous noise, and the wearing experience of hearing loss patients is not good.

Images