【摘要】 提出了一种基于小波变换的新型语音参数提取算法,提高语音识别系统对环境噪声的鲁棒性。由于引入了多分辨率小波分析技术,识别既在高频提供高的频率分辨又在低频提供高的时间分辨率。这样,提出的改进算法在语音词汇的识别更准确的同时,还大大简化了计算。将该算法和传统提取MFCC系数的算法进行了比较,实验结果表明,利用小波计算语音特征具有更优的性能。更多还原

【Abstract】 This paper proposed a novel approach for speech feature extraction,which promoted the robustness of speech recog-nition to noise.Wavelet transform was adopted to get both highest temporal resolution and frequency resolution in different position.So the algorithm not only yield accurate measurements,but also exhibit a low computational cost.The experiment compared traditional MFCC algorithm and this method,results demonstrate that the proposed algorithm is robust and efficient for applications in speech recognition.更多还原