Probability-Weighted Average Algorithm for Mel-Frequency Filter-Bank Vector Reconstruction

LUO Yu; DU Li-min

您当前的位置：

首页 >

文章列表页 >

Probability-Weighted Average Algorithm for Mel-Frequency Filter-Bank Vector Reconstruction

更新时间：2025-07-16

- Probability-Weighted Average Algorithm for Mel-Frequency Filter-Bank Vector Reconstruction
- Acta Electronica Sinica Vol. 32, Issue 10, Pages: 1738-1741(2004)
- 作者机构：
  
  中科院声学所语音交互技术研究中心,北京,100080
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.34
- Published：2004
- 稿件说明：
移动端阅览
LUO Yu, DU Li-min. Probability-Weighted Average Algorithm for Mel-Frequency Filter-Bank Vector Reconstruction[J]. Acta Electronica Sinica, 2004, 32(10): 1738-1741.
DOI：

LUO Yu, DU Li-min. Probability-Weighted Average Algorithm for Mel-Frequency Filter-Bank Vector Reconstruction[J]. Acta Electronica Sinica, 2004, 32(10): 1738-1741. DOI：

摘要

本文提出基于概率加权平均的Mel子带特征数据重建算法.该算法选择

个最优重建结果的概率加权平均作为被加性噪声掩蔽的语音特征分量的估计.实验结果表明

基于概率加权平均的语音特征数据重建算法降低了重建误差

减少了帧间突变现象

增强了Mel子带特征的帧间连续性

从而显著提高了语音识别系统对加性噪声的鲁棒性能.

Abstract

In this paper

probability weighted average (PWA) algorithm is proposed to reconstruct Mel-frequency filter-bank vectors.The probability-weighted average of K-best reconstructed "missing" components of Mel-frequency filter-bank vectors is taken as the estimation of components masked by additive noise.Experimental results show that PWA algorithm can reduce reconstruction error

increase the continuity between neighbor mel-filterbank vectors and greatly improve automatic speech recognition (ASR) system's robustness against additive noise.

关键词

Keywords

references

Views

976

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

全自动中文新闻字幕生成系统的设计与实现

Related Author

郑李磊

谢磊

芦咪咪

王晓暄

杨玉莲

张艳宁

Related Institution

西北工业大学计算机学院陕西省语音与图像信息处理重点实验室

⁰