Related papers: TeCANet: Temporal-Contextual Attention Network for…

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…

The auditory attention decoding (AAD) approach was proposed to determine the identity of the attended talker in a multi-talker scenario by analyzing electroencephalography (EEG) data. Although the linear model-based method has been widely…

Inspired by the tremendous success of deep Convolutional Neural Networks as generic feature extractors for images, we propose TimeNet: a deep recurrent neural network (RNN) trained on diverse time series in an unsupervised manner using…

Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models…

Neural network based speech dereverberation has achieved promising results in recent studies. Nevertheless, many are focused on recovery of only the direct path sound and early reflections, which could be beneficial to speech perception,…

We propose a method for joint multichannel speech dereverberation with two spatial-aware tasks: direction-of-arrival (DOA) estimation and speech separation. The proposed method addresses involved tasks as a sequence to sequence mapping…

Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA) results on a number of speech separation benchmarks. One…

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…

In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data. We propose to add residual connections across timesteps to RNN, which explicitly enhances the…

We investigate the effectiveness of convolutive prediction, a novel formulation of linear prediction for speech dereverberation, for speaker separation in reverberant conditions. The key idea is to first use a deep neural network (DNN) to…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

We propose TF-GridNet for speech separation. The model is a novel deep neural network (DNN) integrating full- and sub-band modeling in the time-frequency (T-F) domain. It stacks several blocks, each consisting of an intra-frame full-band…

With the rising number of interconnected devices and sensors, modeling distributed sensor networks is of increasing interest. Recurrent neural networks (RNN) are considered particularly well suited for modeling sensory and streaming data.…

Deep attractor networks (DANs) perform speech separation with discriminative embeddings and speaker attractors. Compared with methods based on the permutation invariant training (PIT), DANs define a deep embedding space and deliver a more…

The task of speech recognition in far-field environments is adversely affected by the reverberant artifacts that elicit as the temporal smearing of the sub-band envelopes. In this paper, we develop a neural model for speech dereverberation…

The Transformer, a breakthrough architecture in artificial intelligence, owes its success to the attention mechanism, which utilizes long-range interactions in sequential data, enabling the emergent coherence between large language models…

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components,…

Deep neural networks have shown excellent prospects in speech separation tasks. However, obtaining good results while keeping a low model complexity remains challenging in real-world applications. In this paper, we provide a bio-inspired…

Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle with substantial spectral redundancy and the limited non-linear modeling capacity of…

In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then resynthesize waveform…