A field that has directly benefited from the recent advances in deep learning is automatic
speech recognition (ASR). Despite the great achievements of the past decades, however, a …

This is a survey paper that aims to give reviews about that finest architectures of machine
learning, the use of algorithms and the applications of the system and speech and vision …

This survey presents a review of state-of-the-art deep neural network architectures,
algorithms, and systems in speech and vision applications. Recent advances in deep …

In this paper, we summarize recent progresses made in deep learning based acoustic
models and the motivation and insights behind the surveyed techniques. We first discuss …

We describe a large vocabulary speech recognition system that is accurate, has low latency,
and yet has a small enough memory and computational footprint to run faster than real-time …

We study the problem of compressing recurrent neural networks (RNNs). In particular, we
focus on the compression of RNN acoustic models, which are motivated by the goal of …

Several consumer speech devices feature voice interfaces that perform on-device keyword
spotting to initiate user interactions. Accurate on-device keyword spotting within a tight CPU …

Integrated convolutional neural network (CNN) and deep bidirectional long short-term
memory (DBLSTM) based character models have achieved excellent recognition accuracies …

In this paper, we explore the use of attention-based models for online speech recognition
without the usage of language models or searching. Our model is based on an attention …

Recently, deep neural networks (DNNs) significantly outperform Gaussian mixture models in
acoustic modeling for speech recognition. However, the substantial increase in …