Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (29): 73-75.DOI: 10.3778/j.issn.1002-8331.2010.29.020

• 研发、设计、测试 • Previous Articles     Next Articles

Design and simulation of time-frequency features display system for speech signal

WANG Guang-yan1,2,ZHAO Xiao-qun3,WANG Xia1   

  1. 1.School of Information Engineering,Hebei University of Technology,Tianjin 300130,China
    2.School of Information Engineering,Tianjin University of Commerce,Tianjin 300134,China
    3.College of Electronics and Information Engineering,Tongji University,Shanghai 200092,China
  • Received:2010-01-27 Revised:2010-03-22 Online:2010-10-11 Published:2010-10-11
  • Contact: WANG Guang-yan

语音信号时频特征显示系统的设计和仿真

王光艳1,2,赵晓群3,王 霞1   

  1. 1.河北工业大学 信息工程学院,天津 300130
    2.天津商业大学 信息工程学院,天津 300134
    3.同济大学 电子与信息工程学院,上海 200092
  • 通讯作者: 王光艳

Abstract: Although the algorithms for speech processing are plentiful,there are few visualization software platforms which can be used to testify or design some specific algorithms.In this paper,a system platform used for extracting and indicating the time-spectral features of speech signal is designed under the environment of MATLAB GUI.On this platform,the user can load and play the speech signal in different audio formats.Especially,Linear Prediction Cepstrum Coefficient(LPCC) and Mel-Frequency Cepstrum Coefficient(MFCC),which are the two main feature parameters for speech recognition system,can be calculated,saved and displayed on the same panel.The system interface is friendly,as well as it is convenient and interactive for operating.The simulation results demonstrate the accuracy of the background algorithms for time-frequency features extracting.The designed system will provide important and intuitive auxiliary effect on verifying the algorithms and data processing efficiency for the research fields related to speech signal processing.

摘要: 语音信号处理算法众多,但用于语音处理算法验证和开发的可视化研究平台极少。基于MATLAB GUI技术,完成语音信号典型时频特征参数提取和显示系统仿真平台的设计。可实现多种格式音频文件的载入和播放、波形和频谱显示、以及线性预测倒谱系数和美尔倒谱系数的计算、存储和显示等功能。系统界面友好、操作方便,可实现参数的交互输入并控制显示结果。仿真结果验证了相关时频特征参数提取算法的正确性,提高了对算法或数据处理效果的直观认识。

CLC Number: