基于改进感知非均匀谱压缩的鲁棒语音识别算法  

A Robust Speech Recognition Algorithm Based on Improved Perception Non-uniform Spectral Compression

作　　者：张毅[1] 何春江[1] 罗元[1] 徐晓东[2] 童开国[1] 

机构地区：[1]重庆邮电大学智能系统及机器人研究所,重庆400065 [2]电子科技大学自动化学院,四川成都611731

出　　处：《信息与控制》2013年第5期565-569,共5页Information and Control

基　　金：国际科技合作计划资助项目(2010DFA12160)

摘　　要：针对语音识别系统在噪声环境下识别率下降的问题,提出改进的感知非均匀谱压缩特征提取算法,它能在噪声环境下对语音信号进行有效的压缩,并且使训练与识别环境更加匹配,最终达到提高识别率的目的.在智能轮椅平台上进行语音识别验证,结果表明,该算法能有效地提高语音识别系统的鲁棒性,保证语音识别系统在噪声环境下的识别率.To solve the recognition dropping problem of speech recognition systems in noise environment, an improved feature extraction algorithm based on perception non-uniform spectral compression is proposed. The algorithm can realize the effective compression of the speech signals in noise environment and make the training and the recognition environments more matching. So the recognition rate can be improved. The experiment result on the intelligent wheelchair platform shows that the algorithm can effectively enhance the robustness of speech recognition, and can ensure the recognition rate in noise environment.

关 键 词：语音识别 感知非均匀谱压缩 智能轮椅 MEL频率倒谱系数 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]