Voice Activity Detection Algorithm Based on RASTA and SVM 基于RASTA和SVM的话音激活检测算法
A Noise Suppression Method Based on Spectral Subtraction and RASTA for Speech Recognition 用于语音识别的减谱结合RASTA的抗噪声方法
The influences of rapidly changing signals to human perception can be stressed by filtering the relative spectra ( RASTA) for MFCC. 对MFCC进行相对谱(RASTA)滤波,可以突出快变信号对听觉感知的影响。
An enhanced RASTA filtering of speech 语音信号的增强相对谱滤波
We propose an Enhanced RASTA ( ERASTA) technique for speech and speaker recognition. The new method consists of classical RASTA filtering in logarithmic spectrum domain following by another RASTA processing in spectrum domain. 提出了在语音信号对数功率谱域和功率谱域顺序滤波的新的增强RASTA滤波(ERASTA)方法。
The methods of spectral subtraction, RASTA-PLP analysis and the static-dynamic features combination are used for reducing the additive and convolutions interferences and improving the robustness of the extracted features. 采用谱减法、RASTA-PLP法和静态&动态特征组合,以消除语音中加性和卷积干扰和改善抽得特征的顽健性。
A Study for the Application of RASTA on Objective Communication Speech Quality Evaluation RASTA滤波在语音通信质量客观评价中应用的研究
RASTA filtering technique was applied to the extraction of PLP characteristic parameters. 将RASTA滤波技术应用于PLP特征参数的提取中,提高了参数的识别率,取得了好的实验结果。
In the feature extraction module, using a RASTA filtering, VAD and CMS techniques to improve robustness of characteristic parameters to noise and channel, and based on this, the SDC extracted as acoustic characteristic parameters. 在特征提取模块,采用了RASTA滤波,VAD和倒谱域减均值等技术以提高特征参数对噪声和信道的鲁棒性,在此基础上,提取SDC声学特征参数。