一种HHT谱矩阵的车内噪声语音端点检测-计算机工程与应用.PDF

164 2012 ，48 （20 ） Computer Engineering and Applications 计算机工程与应用 一种HHT 谱矩阵的车内噪声语音端点检测 1，2 1 1 1 刘柏森 ，卢志茂 ，金 辉 ，孙美玲 1，2 1 1 1 LIU Baisen , LU Zhimao , JIN Hui , SUN Meiling 1.哈尔滨工程大学 信息与通信工程学院，哈尔滨 150001 2.黑龙江工程学院 电子工程系，哈尔滨 150050 1.College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China 2.Department of Electronic Engineering, Heilongjiang Institute of Technology, Harbin 150050, China LIU Baisen, LU Zhimao, JIN Hui, et al. Voice activity detection with vehicle interior noise based on Hilbert-Huang transform spectral matrix. Computer Engineering and Applications, 2012, 48 （20 ）：164-167. Abstract ：It is difficult to control voice of intelligent vehicles due to vehicle interior noise, which can decrease detection rate of voice obviously. The article presents a detection method based on Hilbert-Huang Transform （HHT ）spectral matrix. The method with frame as a unit processes time, frequency, and amplitude matrix of input signal HHT, and constructs amplitude-time curve by analyzing characteristics of HHT and noise, voice signal amplitude distribution. By estimating front end noise, the method sets threshold automatically for detecting phonetic segment of the whole signal. The result indicates that the method can detect voice activity effectively with vehicle interior heavy noise. Key words ：signal processing; Hilbert-Huang Transform（HHT ）; vehicle interior noise; signal detection; low signal- to-noise ratios 摘 要：由于车内噪声的存在，使语音的检测率降低得非常明显，这给智能汽车的语音控制带来了困难。提出 了一种基于HHT 谱矩阵的检测方法。该方法通过分析HHT 的特点，以及噪声、语音信号的幅度分布特点，以 帧为单位对输入信号HHT 的时、频、幅矩阵进行处理，构建幅值-时间曲线，通过对前端噪声段的估计，自动设 定阈值对整个信号的语音段进行检测。实验结果表明，该方法在车内噪声较强的情况下仍能有效检测语音段。 关键词：信号处理；希尔伯特-黄变换；车内噪声；信号检测；低信噪比 文章编号：1002-8331（2012 ）20-0164-04 文献标识码：A 中图分类号：TP391