… learning be applied to these varying deep learning systems to achieve greater recognition
… methods for ensemble learning with applications specifically to speech-class posterior …

In this paper, we provide an overview of the invited and contributed papers presented at the
special session at ICASSP-2013, entitled “New Types of Deep Neural Network Learning for …

… encouraged increasing research efforts on deep learning with the goal of … deep learning
approaches that are designed to address the noise robustness problem for speech recognition. …

… • In the Introduction, we introduce the readers to the fields of deep learning, NLP, and speech
with a brief history. We present the different areas of machine learning and detail different …

… by Microsoft since the year 2009 in the area of speech using deep learning. The paper …
as well as limitations of deep learning in the area of speech recognition. This was done by …

… on sweeping achievements of deep learning in speech recognition since its initial … of deep
learning in speech recognition systems. Next, more challenging applications of deep learning, …

… in speech recognition performance [37]. Expanding on ideas from recent successes in
deep learning studies, we propose to apply two major DNN architectures, deep denoising …

… is really embodied in deep learning elaborated in this book, … of deep learning for ASR in
2009 or, as our 2014 overview book, were focused on less technical aspects of deep learning for …

… Top speech recognition systems rely on sophisticated … end speech system, called “Deep
Speech”, where deep learning … traditional methods on hard speech recognition tasks while also …

… , English speech recognition … of deep learning in acoustic features and speech attributes,
and combines the two features to propose a deep speech-based English speech recognition …