Related papers: A Tale of Two Lexica Testing Computational Hypothe…

Convolutional neural networks (CNNs) have been tremendously successful in solving imaging inverse problems. To understand their success, an effective strategy is to construct simpler and mathematically more tractable convolutional sparse…

Tree-structured neural networks have proven to be effective in learning semantic representations by exploiting syntactic information. In spite of their success, most existing models suffer from the underfitting problem: they recursively use…

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches.…

Convolutional layers are the core building blocks of Convolutional Neural Networks (CNNs). In this paper, we propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a…

In order to maximize the applicability of sentiment analysis results, it is necessary to not only classify the overall sentiment (positive/negative) of a given document but also to identify the main words that contribute to the…

A promising approach for multi-microphone speech separation involves two deep neural networks (DNN), where the predicted target speech from the first DNN is used to compute signal statistics for time-invariant minimum variance…

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of…

The landscape of deep learning has vastly expanded the frontiers of source code analysis, particularly through the utilization of structural representations such as Abstract Syntax Trees (ASTs). While these methodologies have demonstrated…

This paper explores the application of Convolutional Neural Networks CNNs for classifying emotions in speech through Mel Spectrogram representations of audio files. Traditional methods such as Gaussian Mixture Models and Hidden Markov…

Deep learning models for natural language processing (NLP) are inherently complex and often viewed as black box in nature. This paper develops an approach for interpreting convolutional neural networks for text classification problems by…

This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have…

Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent…

Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion or dilated convolutions, we propose a novel…

Morphological declension, which aims to inflect nouns to indicate number, case and gender, is an important task in natural language processing (NLP). This research proposal seeks to address the degree to which Recurrent Neural Networks…

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…

Recent advances of semantic image segmentation greatly benefit from deeper and larger Convolutional Neural Network (CNN) models. Compared to image segmentation in the wild, properties of both medical images themselves and of existing…

Neural networks have a remarkable capacity for contextual processing--using recent or nearby inputs to modify processing of current input. For example, in natural language, contextual processing is necessary to correctly interpret negation…

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we…

We focus on the word-level visual lipreading, which requires recognizing the word being spoken, given only the video but not the audio. State-of-the-art methods explore the use of end-to-end neural networks, including a shallow (up to three…

The goal of convective storm nowcasting is local prediction of severe and imminent convective storms. Here, we consider the convective storm nowcasting problem from the perspective of machine learning. First, we use a pixel-wise sampling…