Linearized distortion model for robust speech recognition in noisy environments

HE Yong-jun1; HAN Ji-qing1

您当前的位置：

首页 >

文章列表页 >

Linearized distortion model for robust speech recognition in noisy environments

更新时间：2024-10-14

- Linearized distortion model for robust speech recognition in noisy environments
- Vol. 31, Issue 9, Pages: 8-14(2010)
- 作者机构：
  
  1. 哈尔滨工业大学计算机科学与技术学院
  2. 哈尔滨理工大学计算机科学与技术学院
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.34
- Published：2010
- 稿件说明：
移动端阅览
HE Yong-jun1, HAN Ji-qing1. Linearized distortion model for robust speech recognition in noisy environments[J]. 2010, 31(9): 8-14.
DOI：

HE Yong-jun1, HAN Ji-qing1. Linearized distortion model for robust speech recognition in noisy environments[J]. 2010, 31(9): 8-14. DOI：

摘要

针对噪声环境下语音识别的顽健性问题

考虑到梅尔倒谱系数(MFCC

Mel-frequency cepstral coefficient)域的畸变模型高度非线性且难以处理

用分段线性插值函数代替对数函数

提出了一种新的线性畸变模型。在此基础上

导出了噪声参数估计和声学模型补偿方法

无需采用矢量泰勒级数(VTS

vector Taylor series)展开作近似处理

有效避免了模型误差的引入

增强了系统在噪声环境下的顽健性。

Abstract

The robustness of speech recognition system in noisy environments was investigated.The distortion model in Mel-frequency cepstral coefficient（MFCC） domain is highly non-linear and difficult to deal with.A new linear distortion model was proposed by replacing the logarithm operation with its piecewise linear interpolation function.Then the esti-mation of noise parameters and compensation of acoustic models were provided.The proposed method can avoid model error introduced by utilizing linearization methods based on vector Taylor series（VTS） expansion

and significantly im-prove the robustness of recognizer in noisy environments.

关键词

Keywords

references

Views

815

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Chinese semantic and phonological information-based text proofreading model for speech recognition

Semi-fragile video watermarking algorithm for H.264/AVC based on cost strategy

Packet-loss robust scalable authentication algorithm for compressed image streaming

Self-embedding robust digital watermarking algorithm with perfectly blind detection

Robust DWT-HMM image watermarking algorithm optimized with content-adaptive approach

Related Author

Peiliang WU

Yan DOU

Yi LIU

Lingfu KONG

Meiyu ZHONG

Wei-wei ZHANG

Yi-xian YANG

Pei ZHANG

Related Institution

The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province

The Key Laboratory of Software Engineering of Hebei Province

School of Information Science and Engineering, Yanshan University

Information Security Center,Beijing University of Posts and Telecommunications

National Computer Network and Information Security Management Center

AI问答

⁰