| 基于EMD的语音功率谱分析 |
| |
| 引用本文： | 周慧,魏霖静.基于EMD的语音功率谱分析[J].电子设计工程,2012,20(4):162-164. |
| |
| 作者姓名： | 周慧 魏霖静 |
| |
| 作者单位： | 甘肃农业大学信息科学技术学院,甘肃兰州,730070 |
| |
| 摘 要： | 提出了一种基于EMD的功率谱分析法,即先用经验模态分解方法(EMD)将语音信号分解成若干个固有模态函数IMF分量,而后对包含主要信息的IMF分量利用现代参数模型法估计出它们各自的功率谱。文中对不同情感状态下语音数据的分析结果表明,EMD方法能有效地应用于非平稳语音信号的功率谱分析中,可更细致的体现语音信号内在特征。
|
| 关 键 词： | 经验模态分解方法(EMD) 功率谱 语音信号 IMF分量 现代参数模型法 |
Power spectrum analysis of speech signal based on Empirical Mode Decomposition |
| |
| ZHOU Hui,WEI Lin-jing.Power spectrum analysis of speech signal based on Empirical Mode Decomposition[J].Electronic Design Engineering,2012,20(4):162-164. |
| |
| Authors: | ZHOU Hui WEI Lin-jing |
| |
| Affiliation: | (College of Information Science and Technology,Gansu Agricultural University,Lanzhou 730070,China) |
| |
| Abstract: | A new power spectrum analysis of speech signal method based on Empirical Mode Decomposition is presented.First,the speech signal is decomposed into several intrinsic mode functions(IMF) by using empirical mode decomposition(EMD) method.Then,power spectrums of some IMF components which contain main information calculated by modern PSD estimation method.The analysis results of the experimental emotion speech data show that the proposed approach can be applied to the power spectrum analysis of non-stationary speech signal efficiently,can be more detailed inherent characteristics of the speech signal. |
| |
| Keywords: | EMD power spectrum speech signal IMF modem PSD estimation method |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
