New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …

Although great progress has been made in automatic speech recognition, significant
performance degradation still exists in noisy environments. Recently, very deep …

Recently, a new acoustic model based on deep neural networks (DNN) has been
introduced. While the DNN has generated significant improvements over GMM-based …

Recent studies have shown that deep neural networks (DNNs) perform significantly better
than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech …

Recently, supervised classification has been shown to work well for the task of speech
separation. We perform an in-depth evaluation of such techniques as a front-end for noise …

For noise robust speech recognition, data mismatch between training and testing is a
significant challenge. Data augmentation is an effective way to enlarge the size and diversity …

Although great progress has been made in automatic speech recognition, significant
performance degradation still exists in noisy environments. Our previous work has …

We explore time-frequency masking to improve noise robust automatic speech recognition.
Apart from its use as a frontend, we use it for providing smooth estimates of speech and …

This paper describes the extension and optimisation of our previous work on very deep
convolutional neural networks (CNNs) for effective recognition of noisy speech in the Aurora …

Data augmentation is an effective method to increase the size of training data and reduce
the mismatch between training and testing for noise robust speech recognition. Different …