Related papers: Spatially-Augmented Sequence-to-Sequence Neural Di…

We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using minibatch stochastic gradient descent (SGD). Our goal is to…

In this paper, we carry out numerical analysis to prove convergence of a novel sample-wise back-propagation method for training a class of stochastic neural networks (SNNs). The structure of the SNN is formulated as discretization of a…

We present a Spiking Neural Network (SNN) model that incorporates learnable synaptic delays through two approaches: per-synapse delay learning via Dilated Convolutions with Learnable Spacings (DCLS) and a dynamic pruning strategy that also…

Brain-inspired spiking neural networks (SNNs) are recognized as a promising avenue for achieving efficient, low-energy neuromorphic computing. Direct training of SNNs typically relies on surrogate gradient (SG) learning to estimate…

Spoken dialogue is an intuitive form of human-computer interaction, yet current speech language models often remain constrained to turn-based exchanges, lacking real-time adaptability such as user barge-in. We propose a novel duplex speech…

Self-supervised models such as WavLM have demonstrated strong performance for neural speaker diarization. However, these models are typically pre-trained on single-channel recordings, limiting their effectiveness in multi-channel scenarios.…

Temporal processing is vital for extracting meaningful information from time-varying signals. Recent advancements in Spiking Neural Networks (SNNs) have shown immense promise in efficiently processing these signals. However, progress in…

End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…

Driver attention prediction is becoming an essential research problem in human-like driving systems. This work makes an attempt to predict the driver attention in driving accident scenarios (DADA). However, challenges tread on the heels of…

For many practical computer vision applications, the learned models usually have high performance on the datasets used for training but suffer from significant performance degradation when deployed in new environments, where there are…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

Schizophrenia is a debilitating, chronic mental disorder that significantly impacts an individual's cognitive abilities, behavior, and social interactions. It is characterized by subtle morphological changes in the brain, particularly in…

In recent years, self-supervised learning (SSL) models have made significant progress in audio deepfake detection (ADD) tasks. However, existing SSL models mainly rely on large-scale real speech for pre-training and lack the learning of…

In this paper, we propose a quality-aware end-to-end audio-visual neural speaker diarization framework, which comprises three key techniques. First, our audio-visual model takes both audio and visual features as inputs, utilizing a series…

Transformer models have achieved superior performance in various natural language processing tasks. However, the quadratic computational cost of the attention mechanism limits its practicality for long sequences. There are existing…

Spiking neural networks (SNNs), the models inspired by the mechanisms of real neurons in the brain, transmit and represent information by employing discrete action potentials or spikes. The sparse, asynchronous properties of information…

Self-supervised pre-training methods have brought remarkable breakthroughs in the understanding of text, image, and speech. Recent developments in genomics has also adopted these pre-training methods for genome understanding. However, they…

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active…

Traditional sequential recommendation methods assume that users' sequence data is clean enough to learn accurate sequence representations to reflect user preferences. In practice, users' sequences inevitably contain noise (e.g., accidental…

Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target domains. As previous UDA&DG semantic segmentation methods are…