Related papers: The IOA System for Deep Noise Suppression Challeng…

Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning…

AI systems deployed in the real world must contend with distractions and out-of-distribution (OOD) noise that can destabilize their policies and lead to unsafe behavior. While robust training can reduce sensitivity to some forms of noise,…

Studies have shown that in noisy acoustic environments, providing binaural signals to the user of an assistive listening device may improve speech intelligibility and spatial awareness. This paper presents a binaural speech enhancement…

Traditional Active Noise Control (ANC) systems are mostly based on FxLMS algorithms, but such algorithms rely on linear assumptions and are often limited in handling broadband non-stationary noise or nonlinear acoustic paths. Not only that,…

Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…

Deep complex convolution recurrent network (DCCRN), which extends CRN with complex structure, has achieved superior performance in MOS evaluation in Interspeech 2020 deep noise suppression challenge (DNS2020). This paper further extends…

This paper further explores our previous wake word spotting system ranked 2-nd in Track 1 of the MISP Challenge 2021. First, we investigate a robust unimodal approach based on 3D and 2D convolution and adopt the simple attention module…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

The perceptual task of speech quality assessment (SQA) is a challenging task for machines to do. Objective SQA methods that rely on the availability of the corresponding clean reference have been the primary go-to approaches for SQA.…

Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for modern methods that leverage deep neural networks trained to…

The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task,…

Sound processing in the human auditory system is complex and highly non-linear, whereas hearing aids (HAs) still rely on simplified descriptions of auditory processing or hearing loss to restore hearing. Even though standard HA…

We study the problem of learning the objective functions or constraints of a multiobjective decision making model, based on a set of sequentially arrived decisions. In particular, these decisions might not be exact and possibly carry…

Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work. In this work, we propose a novel noise injection-based training scheme for better model robustness.…

Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress…

In this paper, we present a full-reference speech quality prediction model with a deep learning approach. The model determines a feature representation of the reference and the degraded signal through a siamese recurrent convolutional…

Blind Image Quality Assessment (BIQA) aims to evaluate image quality in line with human perception, without reference benchmarks. Currently, deep learning BIQA methods typically depend on using features from high-level tasks for transfer…

Hyperspectral image (HSI) denoising is of crucial importance for many subsequent applications, such as HSI classification and interpretation. In this paper, we propose an attention-based deep residual network to directly learn a mapping…

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current approaches for designing robust losses involve the introduction of noise-robust factors, i.e., hyperparameters, to control the…

For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder's reconstruction compared to standard decoding techniques. Specifically, we propose a recurrent neural network approach for…