Sorry, you need to enable JavaScript to visit this website.

Loudspeaker drivers are subject to nonlinear distortion in the low frequency range at high input levels. In sound zone control, distortion not only reduces the acoustic contrast between zones, but also gives perceived artefacts. Standard sound zone methods, such as acoustic contrast control, apply a constraint to the overall input power, but individual loudspeaker drivers are not controlled and the nonlinear distortion is mainly produced by the loudspeaker drivers with the highest input power.

Our article provides a theoretical analysis of the asymptotic performance of a regression or classification task performed by a simple random neural network. This result is obtained by leveraging a new framework at the crossroads between random matrix theory and the concentration of measure theory. This approach is of utmost interest for neural network analysis at large in that it naturally dismisses the difficulty induced by the non-linear activation functions, so long that these are Lipschitz functions.

Presence of interictal epileptiform discharges (IED) in the electroencephalogram (EEG) is indicative of epilepsy. Automated
software for annotating EEGs of Patients with suspected epilepsy is substantial for diagnosis and management of epilepsy.
A large amount of data is needed for training and evaluating the performance of an effective IED detection system. IEDs occur
infrequently in the EEG of most patients, hence, interictal EEG recordings contain mostly background waveforms. As the first

In this paper, residual redundancy in compressed videos is exploited to alleviate transmission errors using joint source channel arithmetic decoding. A new method is proposed to estimate a priori probability in MAP metric of H.264 intra modes decoder. The decoder generates a decoding tree using a breadth first search algorithm. An introduced statistical model is then implemented stage by stage over the decoding tree.

In this presentation, the effects of quantisation on distributed convex optimisation algorithms are explored via the lens of monotone operator theory. Specifically, by representing transmission quantisation via an additive noise model, we demonstrate how quantisation can be viewed as an instance of an inexact Krasnoselskii-Mann scheme. In the case of two distributed solvers, the Alternating Direction Method of Multipliers and the Primal Dual Method of Multipliers, we further demonstrate how an adaptive quantisation scheme can be constructed to reduce transmission costs between nodes.

In this paper, we present a pruning technique for maximum en- tropy (MaxEnt) language models. It is based on computing the exact entropy loss when removing each feature from the model, and it ex- plicitly supports backoff features by replacing each removed feature with its backoff. The algorithm computes the loss on the training data, so it is not restricted to models with n-gram like features, al- lowing models with any feature, including long range skips, triggers, and contextual features such as device location.

The present work introduces the hybrid consensus alternating direction method of multipliers (H-CADMM), a novel framework for optimization over networks which unifies existing distributed optimization approaches, including the centralized and the decentralized consensus ADMM. H-CADMM provides a flexible tool that leverages the underlying graph topology in order to achieve a desirable sweet-spot between node-to-node communication overhead and rate of convergence -- thereby alleviating known limitations of both C-CADMM and D-CADMM.

In this paper, we analyze how much, how consistent and how accurate data WaveNet-based speech synthesis method needs to be abletogeneratespeechofgoodquality. Wedothisbyaddingartificial noise to the description of our training data and observing how well WaveNet trains and produces speech. More specifically, we add noise to both phonetic segmentation and annotation accuracy, and we also reduce the size of training data by using a fewer number of sentences during training of a WaveNet model.

We present an end-to-end multi-scale Convolutional Neural
Network (CNN) framework for topic identification (topic ID).
In this work, we examined multi-scale CNN for classification
using raw text input. Topical word embeddings are learnt at
multiple scales using parallel convolutional layers. A technique
to integrate verification and identification objectives is
examined to improve topic ID performance. With this approach,
we achieved significant improvement in identification
task. We evaluated our framework on two contrasting

Remote Photoplethysmography (rPPG) is a contactless noninvasive
method for measuring physiological signals such as
the heart rate (HR) using the light reflected from the facial
tissue. Signal decomposition approaches are used to extract
the heart rate signal from the subtle changes in the skin color.
In this paper, we show that a recently proposed signal decomposition
method, namely nonlinear mode decomposition
(NMD), is quite successful in estimating the heart rate signal
from face videos in the presence of subject motion. Experimental