Cart
Create Account
Sign In
Showing 793 - 816 of 23806
The holy grail in deep neural network research is porting the memory- and computation-intensive network models on embedded platforms with a minimal compromise in model accuracy. To this end, we…
In this paper, we aim at solving a distributed machine learning problem under Byzantine attacks. In the distributed system, a number of workers (termed as Byzantine workers) could send arbitrary…
This paper is concerned with the estimation of unknown drift functions of stochastic differential equations (SDEs) from observations of their sample paths. We propose to formulate this as a non-…
Weather radar echo extrapolation has been one of the most important means for weather forecasting and precipitation nowcasting. However, the effective forecasting time of the most current…
The conventional approach to automatic speech recognition in multi-channel reverberant conditions involves a beamforming based enhancement of the multi-channel speech signal followed by a single…
2 views
This paper studies nonconvex quadratically constrained quadratic program (QCQP), which is known to be NP-hard in general. In the past decades, various approximate approaches have been developed to…
Voice conversion (VC) is a task that alters the voice of a person to suit different styles while conserving the linguistic content. Previous state-of-the-art technology used in VC was based on the…
1 views
The traditional parametric approach to Granger causality (GC), based on linear vector autoregressive modeling, suffers from difficulties related to the inaccurate modeling of the generative process.…
To rectify fisheye distortion from a single image, we advance self-supervised learning strategies and propose a unique deep learning model of Fisheye GAN (FE-GAN). Our FEGAN learns pixel-level…
Gathering information about the acoustic environment of urban areas is now possible and studied in many major cities in the world. Part of the research is to find ways to inform the citizen about its…
In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the…
1 views
Check out this discussion about wearable technology from IEEE @ SXSW 2015, featuring John C. Havens (Author), Dr. Leslie Saxon (USC Center for Body Computing) and Heather Schlegel (Futurist).
435 views
Recent studies have showed that convolutional neural networks (CNN) can effectively improve the performance of single image super-resolution (SR). However, previous methods rarely considered long-…
The colorization of gray-scale images has always been a challenging task in computer vision. Recently, novel approaches have been introduced for unsupervised image translation between two domains…
In this paper, we use a novel algorithmic approach to explore dialectal variation in American English speech. Without the need for human annotations, we are able to use a corpus transcribed in text…
We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more…
1 views
In group object tracking, the identification of the group leader can be highly beneficial for predicting the intention and future manoeuvres of objects as well as learning the underlying group…
We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, a data-driven…
Modeling the relationship between natural speech and a recorded electroencephalogram (EEG) helps us understand how the brain processes speech and has various applications in neuroscience and brain-…
Mobile-edge computing (MEC) is a promising technology to support computation-intensive and delay-sensitive applications at smart devices by offloading their local tasks to the network edge. In this…
At SXSW 2015, Jessica Colao (Director of Partnerships, iHub) provided context on this explosion in mobile innovation in Africa and explained why innovators in Africa value relationships over…
373 views
Supervised deep learning has gained significant attention for speech enhancement recently. The state-of-the-art deep learning methods perform the task by learning a ratio/binary mask that is applied…
In this paper, we propose a deep neural network based matrix completion approach for Internet of Things (IoT) localization. In the proposed method, we recast Euclidean distance matrix completion…
In speech enhancement, the use of supervised algorithms in the form of deep neural networks (DNNs) has become tremendously popular in recent years. The target function of the DNN (and the associated…