The popularity of Convolutional Neural Network (CNN) models and the ubiquity of CPUs
imply that better performance of CNN model inference on CPUs can deliver significant gain …

自动语音识别(ASR) 技术的目的是让机器能够“听懂” 人类的语音, 将人类语音信息转化为可读的
文字信息, 是实现人机交互的关键技术, 也是长期以来的研究热点. 最近几年 …

Since convolutional neural networks (CNNs) achieved top performance on the ImageNet
task in 2012, deep learning has become the preferred approach to addressing computer …

This paper presents a two-timescale duplex neurodynamic system for constrained biconvex
optimization. The two-timescale duplex neurodynamic system consists of two recurrent …

Recurrent neural network language models (RNNLMs) have recently become increasingly
popular for many applications including speech recognition. In previous research RNNLMs …

Recurrent neural network language models have enjoyed great success in speech
recognition, partially due to their ability to model longer-distance context than word n-gram …

In recent years, recurrent neural network language models (RNNLMs) have become
increasingly popular for a range of applications including speech recognition. However, the …

In recent years recurrent neural network language models (RNNLMs) have been
successfully applied to a range of tasks including speech recognition. However, an …

In this paper, we propose a novel neural network structure, namely\emph {feedforward
sequential memory networks (FSMN)}, to model long-term dependency in time series …

While recurrent neural networks can motivate cross-sentence language modeling and its
application to automatic speech recognition (ASR), corresponding modifications of the …