相关论文: Improving performance and inference on audio class…

Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to…

In this work we propose approaches to effectively transfer knowledge from weakly labeled web audio data. We first describe a convolutional neural network (CNN) based framework for sound event detection and classification using weakly…

Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not…

The paper studies the problem of robust classification of digitally modulated signals using capsule networks and cyclic cumulant (CC) features extracted by cyclostationary signal processing (CSP). Two distinct datasets that contain similar…

This paper proposes an noise type classification aided attention-based neural network approach for monaural speech enhancement. The network is constructed based on a previous work by introducing a noise classification subnetwork into the…

Many state-of-the-art systems for audio tagging and sound event detection employ convolutional recurrent neural architectures. Typically, they are trained in a mean teacher setting to deal with the heterogeneous annotation of the available…

Audio-based multimedia retrieval tasks may identify semantic information in audio streams, i.e., audio concepts (such as music, laughter, or a revving engine). Conventional Gaussian-Mixture-Models have had some success in classifying a…

Continual Learning aims to learn from a stream of tasks, being able to remember at the same time both new and old tasks. While many approaches were proposed for single-class classification, multi-label classification in the continual…

Combining multiple machine learning models into an ensemble is known to provide superior performance levels compared to the individual components forming the ensemble. This is because models can complement each other in taking better…

Residual learning is a recently proposed learning framework to facilitate the training of very deep neural networks. Residual blocks or units are made of a set of stacked layers, where the inputs are added back to their outputs with the aim…

High performance ultrasonic sensor hardware is mainly used in medical applications. Although, the development in automotive scenarios is towards autonomous driving, the ultrasonic sensor hardware still stays low-cost and low-performance,…

In this project, we worked on speech recognition, specifically predicting individual words based on both the video frames and audio. Empowered by convolutional neural networks, the recent speech recognition and lip reading models are…

Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization…

Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a…

A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a…

Capsule networks(CapsNet) are recently proposed neural network models with new processing layers, specifically for entity representation and discovery of images. It is well known that CapsNet have some advantages over traditional neural…

This dissertation presents several novel deep-learning (DL)-based approaches for classifying digitally modulated signals, one method of which involves the use of capsule networks (CAPs) together with cyclic cumulant (CC) features of the…

Past few years have witnessed exponential growth of interest in deep learning methodologies with rapidly improving accuracies and reduced computational complexity. In particular, architectures using Convolutional Neural Networks (CNNs) have…

Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train…

The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large…