A channel-weighting method for speech recognition using wavelet decompositions

Proceedings of APCCAS'94 - 1994 Asia Pacific Conference on Circuits and Systems Pub Date : 1994-12-05 DOI:10.1109/APCCAS.1994.514604

Jyh-Shing Shyuu, Jhing-Fa Wang, Chung-Hsien Wu

引用次数: 2

Abstract

A decomposition of signal into a set of frequency channels of equal bandwidth on a logarithmic scale, i.e., an analysis of the signal using constant Q filters, using wavelet and multiresolution analysis is used in this paper to derive cepstrum features of different spatial frequency bands. Based on the decompositions, each channel is modeled as a Bayesian subnetwork and each subnetwork is weighted by a weighting algorithm. The distortions for speech recognition between a reference model and the input vectors are then computed by summing the weighted scores of all decomposed channels. The experimental results show that the recognition rate of this method is superior to those non-weighting methods.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于小波分解的语音识别信道加权方法

本文将信号在对数尺度上分解为一组等带宽的频率通道，即使用定Q滤波器对信号进行分析，并使用小波和多分辨率分析来推导不同空间频段的倒谱特征。在此基础上，将每个信道建模为一个贝叶斯子网，并通过加权算法对每个子网进行加权。然后通过对所有分解通道的加权分数求和来计算参考模型和输入向量之间的语音识别失真。实验结果表明，该方法的识别率优于非加权方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Proceedings of APCCAS'94 - 1994 Asia Pacific Conference on Circuits and Systems

自引率

0.00%

发文量

期刊最新文献

Area-time optimal digital BiCMOS carry look-ahead adder Hierarchical circuit optimization for analog LSIs using device model refining Decomposition-based 2-D variable digital filter design Artificial neural networks-learning and generalization Nonlinear gradient-based edge detection algorithms in the telesign system