Related papers: Continuous Speech Separation with Recurrent Select…

Learning a matching function between two text sequences is a long standing problem in NLP research. This task enables many potential applications such as question answering and paraphrase identification. This paper proposes Co-Stack…

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…

While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance…

Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion…

We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed…

In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a…

Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational…

This paper presents a novel approach to advancing artificial intelligence (AI) through the development of the Complex Recurrent Spectral Network ($\mathbb{C}$-RSN), an innovative variant of the Recurrent Spectral Network (RSN) model. The…

Deep neural network with dual-path bi-directional long short-term memory (BiLSTM) block has been proved to be very effective in sequence modeling, especially in speech separation, e.g. DPRNN-TasNet \cite{luo2019dual}. In this paper, we…

As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper, a new deep learning structure for speech enhancement is…

Speaker extraction aims to extract target speech signal from a multi-talker environment with interference speakers and surrounding noise, given the target speaker's reference information. Most speaker extraction systems achieve satisfactory…

This paper presents a new input format, channel-wise subband input (CWS), for convolutional neural networks (CNN) based music source separation (MSS) models in the frequency domain. We aim to address the major issues in CNN-based…

Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an…

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…

In this paper, we propose a single-channel speech dereverberation system (DeReGAT) based on convolutional, bidirectional long short-term memory and deep feed-forward neural network (CBLDNN) with generative adversarial training (GAT). In…

Continually learning to segment more and more types of image regions is a desired capability for many intelligent systems. However, such continual semantic segmentation suffers from the same catastrophic forgetting issue as in continual…

Speech separation involves extracting an individual speaker's voice from a multi-speaker audio signal. The increasing complexity of real-world environments, where multiple speakers might converse simultaneously, underscores the importance…

Memory-efficient continuous Sign Language Translation is a significant challenge for the development of assisted technologies with real-time applicability for the deaf. In this work, we introduce a paradigm of designing recurrent deep…