Short-wave channel voice enhancement method

Abstract

The invention discloses a short-wave channel speech enhancement method, and belongs to the technical field of communication. According to the invention, a neural network is applied to a short-wave communication voice denoising module, and the same convolutional neural networks based on mapping are selected according to the performance requirements and characteristics of Anti-fading Net and Denoising Net, so that a better noise suppression effect can be achieved; a convolutional neural network denoising model Denoising Net is combined with an existing classic unsupervised speech enhancement algorithm OMLSA, the denoising advantages of the two algorithms are reserved in an equal gain combination mode, and therefore the de-noised speech quality of a Denoising Net or OMLSA algorithm which is independently used is improved; and thirdly, by stacking the two convolutional neural networks with simple structures, a better denoising effect than that of a common neural network with a complex structure is obtained.

Description

technical field [0001] The invention belongs to the technical field of communication, and relates to a short-wave speech enhancement method using a neural network combined with a non-supervised algorithm. Background technique [0002] Short-wave communication realizes long-distance communication through the ionosphere. It is an indispensable last means of communication for emergency and military communications. At the same time, it is also popular among amateur radio enthusiasts due to its low cost and high flexibility of communication equipment. Due to the time-varying characteristics of the ionosphere, the short-wave real-time passable frequency band is very narrow, and the voice signal usually adopts the analog single-sideband (Single-sideband, SSB) modulation method, and the quality of the voice signal received after long-distance transmission is often poor, seriously Affect the hearing comfort; because the SSB signal cannot adopt the method of digital signal processing ...

AI Technical Summary

Problems solved by technology

[0004] In recent years, with the rapid development and wide application of deep learning, speech enhancement methods based on deep learning have become the main research direction of speech enhancement. These methods mainly include three types: masking-based, mapping-based and end-to-end. Mapping-based methods It is more effective at low SNR, while masking-based methods perform better at high SNR. End-to-end methods seem to have more development potential, but they are more computationally intensive and often require complex model structures.

Images