基于MUSIC/MNM谱估计的鲁棒语音特征提取  

Robust Speech Feature Extraction Based on MUSIC / MNM Spectrum Estimation

作　　者：张毅[1] 汪培培[2] 罗元[3] 

机构地区：[1]重庆邮电大学先进制造工程学院,400065 [2]重庆邮电大学自动化学院,重庆400065 [3]重庆邮电大学光电工程学院,重庆400065

出　　处：《信息与控制》2016年第3期355-360,共6页Information and Control

基　　金：国家自然科学基金资助项目(60905066);科技部国际合作项目(2010DFA12160)

摘　　要：针对语音识别系统受噪声干扰识别率急剧下降的问题,通过分析传统的鲁棒语音特征提取方法在语音信号谱估计方面的不足,提出一种在不同信噪比下都具有较好鲁棒性和识别性能的语音特征提取算法.该算法结合多信号分类法(MUSIC)和最小模法(minimum-norm method,MNM)来进行谱估计.接着在移动机器人平台上进行验证实验,结果表明:该算法能有效的提高语音识别率,增强语音识别鲁棒性能.Due to the sharp decline in the recognition rate from noise interference in speech recognition systems,there are limitations in the spectrum estimation of speech signals in traditional robust speech feature extraction methods. In this paper,we discuss these limitations and propose a new speech feature extraction method with better robustness and recognition performance under different signal-to-noise ratios（ SNRs）. In the new method,spectrum estimation involves the combination of a multiple signal classification（ MUSIC） method and a minimum-norm method（ MNM）. We conduct a verification test of the new method on mobile robot platforms and the results show that it has a higher recognition rate and better robustness in speech recognition.

关 键 词：多信号分类法(MUSIC) 最小模法(MNM) 特征提取 鲁棒性 语音识别 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]