Related papers: Adaptive Per-Channel Energy Normalization Front-en…

In this paper, adaptive neural control (ANC) is investigated for a class of strict-feedback nonlinear stochastic systems with unknown parameters, unknown nonlinear functions and stochastic disturbances. The new controller of adaptive neural…

Selective fixed-filter active noise control (SFANC) is a novel approach capable of mitigating noise with varying frequency characteristics. It offers faster response and greater computational efficiency compared to traditional adaptive…

Continual learning involves training neural networks incrementally for new tasks while retaining the knowledge of previous tasks. However, efficiently fine-tuning the model for sequential tasks with minimal computational resources remains a…

Acoustic echo cancellation (AEC) is designed to remove echoes, reverberation, and unwanted added sounds from the microphone signal while maintaining the quality of the near-end speaker's speech. This paper proposes adaptive speech quality…

This paper proposes an adaptive neural-compilation framework to address the problem of efficient program learning. Traditional code optimisation strategies used in compilers are based on applying pre-specified set of transformations that…

Recently, conformer-based end-to-end automatic speech recognition, which outperforms recurrent neural network based ones, has received much attention. Although the parallel computing of conformer is more efficient than recurrent neural…

Most neural-network based speaker-adaptive acoustic models for speech synthesis can be categorized into either layer-based or input-code approaches. Although both approaches have their own pros and cons, most existing works on speaker…

Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective…

The design of codes for feedback-enabled communications has been a long-standing open problem. Recent research on non-linear, deep learning-based coding schemes have demonstrated significant improvements in communication reliability over…

In this paper, we combine communication-theoretic laws with known, practically verified results from circuit theory. As a result, we obtain closed-form theoretical expressions linking fundamental system design and environment parameters…

Previous acoustic transfer methods rely on extensive precomputation and storage of data to enable real-time interaction and auditory feedback. However, these methods struggle with complex scenes, especially when dynamic changes in object…

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Nonlinear models are known to provide excellent performance in real-world applications that often operate in non-ideal conditions. However, such applications often require online processing to be performed with limited computational…

Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called "adversarial examples". In this work, we propose a new feedforward CNN that improves robustness in the presence of…

Practical natural language processing (NLP) tasks are commonly long-tailed with noisy labels. Those problems challenge the generalization and robustness of complex models such as Deep Neural Networks (DNNs). Some commonly used resampling…

Recent studies have shown that post-deployment adaptation can improve the robustness of speech enhancement models in unseen noise conditions. However, existing methods often incur prohibitive computational and memory costs, limiting their…

Advances in miniaturised implantable neural electronics have paved the way for therapeutic brain-computer interfaces with clinical potential for movement disorders, epilepsy, and broader neurological applications. This paper presents a…

Radio Frequency (RF) sensing holds the potential for enabling pervasive monitoring applications. However, modern sensing algorithms imply complex operations, which clash with the energy-constrained nature of edge sensing devices. This calls…

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…

Front-end personalization has traditionally relied on static designs or rule-based adaptations, which fail to fully capture user behavior patterns. This paper presents an AI driven approach for dynamic front-end personalization, where UI…