Related papers: Global Structure-Aware Drum Transcription Based on…

Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging. Recent works have shown that despite stacking multiple layers, the receptive field of CNNs remains severely limited.…

In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of all…

Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in…

Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods that rely on synthesized metal artifacts for training. However, as synthesized data may not accurately simulate…

Anomaly detection techniques enable effective anomaly detection and diagnosis in multi-variate time series data, which are of major significance for today's industrial applications. However, establishing an anomaly detection system that can…

Deep Neural Networks (DNNs) based semantic segmentation of the robotic instruments and tissues can enhance the precision of surgical activities in robot-assisted surgery. However, in biological learning, DNNs cannot learn incremental tasks…

This paper describes a statistically-principled semi-supervised method of automatic chord estimation (ACE) that can make effective use of music signals regardless of the availability of chord annotations. The typical approach to ACE is to…

Graph Attention Network (GAT) is a graph neural network which is one of the strategies for modeling and representing explicit syntactic knowledge and can work with pre-trained models, such as BERT, in downstream tasks. Currently, there is…

The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain.…

How can we process a piece of recorded music to detect and visualize the onset of each instrument? A simple, interpretable approach is based on partially fixed nonnegative matrix factorization (NMF). Yet despite the method's simplicity,…

The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a…

Random Matrix Theory (RMT) is applied to analyze weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception, and smaller models trained from scratch, such as LeNet5…

Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition. In this work, we propose an attention-based neural network model for joint intent detection and slot…

Accurate traffic prediction in real time plays an important role in Intelligent Transportation System (ITS) and travel navigation guidance. There have been many attempts to predict short-term traffic status which consider the spatial and…

Neighborhood-aware tokenized graph Transformers have recently shown great potential for node classification tasks. Despite their effectiveness, our in-depth analysis of neighborhood tokens reveals two critical limitations in the existing…

Data-driven approaches to automated machine condition monitoring are gaining popularity due to advancements made in sensing technologies and computing algorithms. This paper proposes the use of a deep learning model, based on Long…

We propose Beat Transformer, a novel Transformer encoder architecture for joint beat and downbeat tracking. Different from previous models that track beats solely based on the spectrogram of an audio mixture, our model deals with demixed…

Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism. Consequently, Transformer language models poorly capture long-tail…

The detection of anomalous tissue regions (ATRs) within affected tissues is crucial in clinical diagnosis and pathological studies. Conventional automated ATR detection methods, primarily based on histology images alone, falter in cases…

Arbitrary-scale super-resolution (ASSR) aims to learn a single model for image super-resolution at arbitrary magnifying scales. Existing ASSR networks typically comprise an off-the-shelf scale-agnostic feature extractor and an arbitrary…