.png){kind=icon}
返回
Feature compensation incorporating modeling error statistics
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2006.891334.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this letter, we propose a novel approach to feature compensation for robust speech recognition in noisy environments. We analyze the error distribution of speech corruption model in the log spectral domain and represent the statistics as functions with respect to the signal-to-noise ratio. The proposed algorithm incorporates modeling error statistics into the interacting multiple model technique and shows a performance improvement over the AURORA2 speech recognition task.
Keyword:
feature compensation
modeling error statistics
robust speech recognition
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
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏
The science and application of learning agility: Introduction to the special issue.学习敏捷性的科学与应用：专题引言。
PREAI
分享收藏分享收藏Malignant sarcoma masquerading as a pseudotumour in a patient with mild haemophilia恶性肉瘤伪装成假性肿瘤，发生在轻度血友病患者中
PREAI
分享收藏 没有更多内容
没有更多内容