.png){kind=icon}
返回
Maximum Likelihood Nonlinear Transformations Based on Deep Neural Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2016.2594255.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Feature transformations are commonly used in speech recognition to account for distribution mismatches between the source and target domains (also referred to as covariate shift). Linear (affine) or piecewise linear transformations are typically considered. In this paper, we present deep neural network (DNN) based nonlinear feature transformations estimated under the maximum likelihood criterion. We use the hidden Markov model (HMM) to model speech feature sequences and features in each HMM state assume a Gaussian mixture model (GMM) distribution. The network is pre-trained close to a linear transformation followed by a fine-tuning using the gradient descent algorithm. Due to the nonlinearity, the gradients and the partition functions of GMM-HMM state distributions are evaluated using the Monte Carlo (MC) method based on importance sampling. In addition, a deep stacked architecture is proposed to hierarchically build a DNN as a series of sub-networks with each representing a nonlinear transformation itself, which can be learned using a block-wise learning strategy. Applications of the proposed nonlinear transformations in speaker/environment adaptation and acoustic modeling in large vocabulary continuous speech recognition tasks show its superior performance over the widely-used constrained maximum likelihood linear regression (CMLLR).
Keyword:
Automatic speech recognition
deep neural network
importance sampling
monte Carlo
nonlinear transformation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Real-time and offline techniques for identifying obstructive sleep apnea patients用于识别阻塞性睡眠呼吸暂停患者的实时和离线技术
PREAI
分享收藏
Solvent effect on the conformation of the hydroxymethyl group established by molecular dynamics simulations of methyl‐β‐D‐glucoside in water.png)
Biopolymers
BiopolymersIF0
PREAI
分享收藏Autocatalytic phase separation and graded co-continuous morphology generated by photocuringSoft Matter
Soft MatterIF0
PREAI
分享收藏Cross-linkable Polymer Matrix for Enhanced Thermal Stability of Succinonitrile-based Polymer Electrolyte in Lithium Rechargeable Batteries可交联聚合物基质，用于增强锂可充电电池中基于丁二腈的聚合物电解质的热稳定性
OAAI
OAAI分享收藏
查看更多内容