DeepLabV3+ Vision Transformer for Visual Bird Sound Denoising

Abstract

Audio denoising is a task to improve the perceptual quality of noisy audio signals. There is still residual noise after the denoising of noisy signals, which will affect the quality of audio data. Traditional and deep learning-based methods are still limited to the manual addition of artificial noise or low-frequency noise. Recently, audio denoising has been transformed into an image segmentation problem, and deep neural networks have been applied to solve this problem. However, its performance is limited to shallow image segmentation models. This paper proposes a novel vision transformer model for visual bird sound denoising, combining a pyramid transformer and DeepLabV3+ network (named PtDeepLab) to filter out the noise. The proposed PtDeepLab model is based on the pyramid transformer, which generates long-range and multiscale representations. The PtDeepLab model can achieve intuitive noise reduction in audio, which helps to separate clean audio from the mixture signal. Extensive experimental results showed that the proposed model has a better denoising performance than state-of-the-art methods.

ADM-SLAM: Accurate and Fast Dynamic Visual SLAM with Adaptive Feature Point Extraction, Deeplabv3pro, and Multi-View Geometry

“…Among them, the encoder module is the cornerstone of the whole structure, which is responsible for extracting deep semantic features from images. The main body of the encoder is a Deep Convolutional Neural Network (DCNN) [ 36 , 37 ], which can employ a variety of backbone networks such as ResNet [ 38 ], Xception [ 39 ], or MobileNetV2 [ 40 ], which provide the basic feature extraction capabilities for the model. In order to capture a wider range of contextual information without losing spatial resolution, the encoder uses inflated convolution instead of traditional convolution.…”