Related papers: Frequency Gating: Improved Convolutional Neural Ne…

We introduce Multi-Frame Cross-Entropy training (MFCE) for convolutional neural network acoustic models. Recognizing that similar to RNNs, CNNs are in nature sequence models that take variable length inputs, we propose to take as input to…

Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our…

Gravity inversion is the problem of estimating subsurface density distributions from observed gravitational field data. We consider the two-dimensional (2D) case, in which recovering density models from one-dimensional (1D) measurements…

Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input. To remedy this issue, we propose a self-attention layer…

Previous research in speech enhancement has mostly focused on modeling time or time-frequency domain information alone, with little consideration given to the potential benefits of simultaneously modeling both domains. Since these domains…

The classification of sentences is very challenging, since sentences contain the limited contextual information. In this paper, we proposed an Attention-Gated Convolutional Neural Network (AGCNN) for sentence classification, which generates…

Structural damage detection has become an interdisciplinary area of interest for various engineering fields, while the available damage detection methods are being in the process of adapting machine learning concepts. Most machine learning…

There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural Machine Translation (NMT). The vanilla NMT model…

Recent studies have put into question the commonly assumed shift invariance property of convolutional networks, showing that small shifts in the input can affect the output predictions substantially. In this paper, we analyze the benefits…

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Neural networks are vulnerable to input perturbations such as additive noise and adversarial attacks. In contrast, human perception is much more robust to such perturbations. The Bayesian brain hypothesis states that human brains use an…

Advertising and feed ranking are essential to many Internet companies such as Facebook. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role. In recent years, many neural…

This paper examines three generic strategies for improving the performance of neuro-evolution techniques aimed at evolving convolutional neural networks (CNNs). These were implemented as part of the Evolutionary eXploration of Augmenting…

This paper proposes a deep neural network (DNN)-based multi-channel speech enhancement system in which a DNN is trained to maximize the quality of the enhanced time-domain signal. DNN-based multi-channel speech enhancement is often…

Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…

Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech…

Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting…

Interpretability work on the convolutional layers of CNNs has primarily focused on computer vision, but some studies also explore correspondences between the latent space and the output in the audio domain. However, it has not been…

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the…