搜索资源列表
vq
- 说话人识别是语音识别的一种特殊方式,其目的不是识别语音内容,而是识别说话人是谁,即从语音信号中提取个人特征。采用矢量量化(VQ)可避免困难的语音分段问题和时间归整问题,且作为一种数据压缩手段可大大减少系统所需的数据存储量。本文提出了识别特征选取采用复倒谱特征参数和对应用VQ的说话人识别系统改进的一种方法。当用于训练的数据量较小时,复倒谱特征可以得到比较稳定的识别性能。VQ的改进方法避免了说话人识别系统的训练时间与使用时间相差过长从而导致系统的性能明显下降以及若利用自相关函数带来的大量运算。-Sp
lpcar2cc
- To convert ar filter to complex cepstrum -To convert ar filter to complex cepstrum CC
Research_0n_Speech_Cepstral_Features
- 该文在研究基于线性预测倒谱和非线性MEL刻度倒谱特征的基础上,研究了LPCC和MFCC参数提取的算法原理及提取算法,提出了一级、二级差分倒谱特征参数的提取算法。识别实验验证了MFCC参数的鲁棒性优于LPCC参数。-In this paper, research is based on linear prediction and nonlinear MEL Cepstrum Cepstrum scale, based on studies of LPCC and MFCC parameter ex
vm
- Owing to the broad application value of audio watermarking in remote transmission and mobile extraction, it is very important to study watermarking approaches against A/D and D/A conversion. Based on wavelet decomposition and cepstrum technol
amorph
- Owing to the broad application value of audio watermarking in remote transmission and mobile extraction, it is very important to study watermarking approaches against A/D and D/A conversion. Based on wavelet decomposition and cepstrum technol
vm2
- Owing to the broad application value of audio watermarking in remote transmission and mobile extraction, it is very important to study watermarking approaches against A/D and D/A conversion. Based on wavelet decomposition and cepstrum technol
voice
- 采用增减特征分量的方法研究了MFCC 各维倒谱分量对说话人识别和语音识别的贡献-Changes in characteristics of components using the method of the MFCC cepstrum of each dimensional component of the speaker recognition and speech recognition of the contribution
melcepst
- melcepst implements a mel-cepstrum front end for a recogniser
chapter5_2
- 同样利用我到北京区为例,用倒谱法求这句语音的基因周期-Also use me to the District, Beijing, for example, cepstrum and the phrase Voice genes cycle
save_words
- cepstrum plot for feature extraction
2007-Thesis-A-Kepstrum-Approach-to-Real-Time-Spee
- A Cepstrum Approach to Real-Time Speech Enhancement
DAOPUFA1234
- 较为详细的介绍倒谱法,传统倒谱法以及对倒谱法的改进算法,以及对倒谱法进行MATLAB实验-A detailed introduction of cepstrum method, the traditional cepstrum method, and the cepstrum method of improved algorithm, and MATLAB experiments of cepstrum method
cep2spec
- matlab code for cepstrum
lpcc
- 这是应用MATLAB求解线性预测倒谱的程序代码,验证有效-this is the application of MATLAB to solve linear predictive cepstrum code, validated
MINI-PRO
- The slides contain deep understanding of the algorithm mfcc ie mel frequency cepstrum coefficients
mfcc
- mfcc mel frequency cepstrum coff good
qun_v19
- 最终的权值矩阵就是滤波器的系数,分析了该信号的时域、频域、倒谱,循环谱等,最大信噪比的独立分量分析算法。- The final weight matrix is ??the filter coefficient, Analysis of the signal time domain, frequency domain, cepstrum, cyclic spectrum, etc. SNR largest independent component analysis algorithm.
jun-V0.7
- 有井曲线作为输入可计算其地震波的衰减,针对EMD方法的不足,分析了该信号的时域、频域、倒谱,循环谱等。- There is a well attenuation curve as input to calculate its seismic waves, For lack of EMD, Analysis of the signal time domain, frequency domain, cepstrum, cyclic spectrum, etc.
cxpvf
- 一种基于多文档得图像合并技术,分析了该信号的时域、频域、倒谱,循环谱等,包括脚本文件和函数文件形式。- Based on multi-document image obtained combining technique, Analysis of the signal time domain, frequency domain, cepstrum, cyclic spectrum, etc. Including scr ipt files and function files in the fo
pqgwe
- 是国外的成品模型,脉冲响应的相关分析算法并检验,分析了该信号的时域、频域、倒谱,循环谱等。- Foreign model is finished, Related impulse response analysis algorithm and inspection, Analysis of the signal time domain, frequency domain, cepstrum, cyclic spectrum, etc.