搜索资源列表
代码
- MATLAB 代码 第1章 BP神经网络的数据分类——语音特征信号分类 第2章 BP神经网络的非线性系统建模——非线性函数拟合 第3章 遗传算法优化BP神经网络——非线性函数拟合 第4章 神经网络遗传算法函数极值寻优——非线性函数极值寻优 第5章 基于BP_Adaboost的强分类器设计——公司财务预警建模 第6章 PID神经元网络解耦控制算法——多变量系统控制 第7章 RBF网络的回归--非线性函数回归的实现 ....等58章(MATLAB code The first
chapter1
- BP神经网络的数据分类——语音特征信号分类(Data Classification of BP Neural Network - Classification of Speech Characteristic Signals)
drtoolbox
- 这是一款比较全面的语音特征降维工具箱，包含了目前常用的34种语音特征降维方法的matlab程序(This is a comprehensive speech feature reduction tool kit, including the current use of 34 phonetic feature reduction methods in matlab program)
YCL
- 对信号进行梅尔倒谱系数特征采集之前的预处理，包括分帧加窗、基于短时能量的双门限判别、除噪、预加重等(The preprocessing of Mel cepstrum coefficients before the signal is carried out, including frame windowing, double threshold discrimination based on short-time energy, denoising and pre emphasis)
audio-compare
- 对语音进行mfcc特征提取，拥有自己的vad模块(MFCC feature extraction of speech, and own VAD module)
107551700第三次作业
- 根据短时傅里叶变换原理，计算并显示该语音段的短时幅度谱和功率谱；根据语谱图显示原理，编程实现该语音段语谱图的计算和显示，并尽量多地分析出语谱图包含的语音特征信息,用MATLAB提供的倒谱计算函数，显示该语音段的复倒谱和倒谱(According to the principle of short-term Fourier transform, the short range spectrum and power spectrum of the speech segment are calculat
MFCC0
- 关于语音特征的提取，MFCC梅尔倒谱系数，挺有效的。。。。(Speech feature extraction, MFCC Mel cepstrum coefficient)
short_zero_crossing_rate
- 语音信号的短时过零率求取，此过程为语音信号的一个重要特征提取过程，可用于端点检测等过程。(This process is an important feature extraction process for speech signals and can be used for endpoint detection and other processes.)
语音聚类示例
- 实验示例是基于语音中的mfcc，语音倒谱特征来进行聚类，先利用训练样本来计算训练样本聚类中心（用到了lbg算法），之后再进行分类。 注意：使用代码时需要自己更改文件路径。(This example is based on the MFCC in speech and the feature of speech Cepstrum to cluster. First, the training sample is used to calculate the training sample clus
基于DTW算法的语音识别系统
- 通过语音分帧、端点检测、特征提取、DTW算法，实现多字语音识别(Through speech segmentation, endpoint detection, feature extraction and DTW algorithm, multi word speech recognition is realized.)
HMM with skips and single Diagonal Gaussian
- 以MFCC作为特征参数，利用HMM算法进行语音识别(Speech recognition using HMM algorithm)
voice_wav_frequency
- matlab语音信号分析时域频域，加窗，降噪滤波，端点检测，时域特征和频域特征提取(Matlab speech signal analysis in time domain, frequency domain, windowing, denoising, filtering, endpoint detection, time domain feature and frequency domain feature extraction.)
LPCC
- 线性预测倒谱系数（Linear Prediction Cepstrum Coefficient,LPCC）是线性预测系数（Linear Prediction Coefficient,LPC）在倒谱域中的表示。该特征是基于语音信号为自回归信号的值设，利用线性预测分析获得倒谱系数。(Linear Prediction Cepstrum Coefficient)
moco
- 语音识别领域的经典论文实现，提供一个可训练的数学模型以预测语音特征(provide a s2s model for speech synthesis and network prediction with python and, e2e solution for production of google)
语音信号的采集与分析(毕业论文)
- 本文简要介绍了语音信号采集与分析的发展史以及语音信号的特征、采集与分析方法，并通过PC机录制自己的一段声音，运用Matlab进行仿真分析，最后加入噪声进行滤波处理，比较滤波前后的变化(This paper briefly introduces the history of the development of speech signal acquisition and analysis, the feature of speech signal, the method of collecting
3809
- 语音识别类文件，能识别0到9 预处理特征参数提取(It is good to use,It can carry out digit recognition, including preprocessing and feature parameter extraction.)
程序
- 录制语音信号， 编写 matlab 代码分析所录制的语音信号， 观察语音信号中蕴含的 alpha 分布， 并进行 alpha 分布的拟合， 对语音信号及其 alpha 特征进行分析(Record speech signals, write matlab code to analyze the recorded speech signals, observe the alpha distribution contained in the speech signals, and fit the a
171724210736171
- MFCC：Mel频率倒谱系数的缩写。Mel频率是基于人耳听觉特性提出来的，它与Hz频率成非线性对应关系。Mel频率倒谱系数(MFCC)则是利用它们之间的这种关系，计算得到的Hz频谱特征。(Speech signal feature extraction)
基于MFCC的GMM的语音识别
- 基于MFCC的GMM的语音识别，先是通过MFCC提取语音信号的特征向量，然后用GMM进行分类识别(Voice recognition of GMM based on MFCC.First, the feature vectors of speech signals are extracted through MFCC, and then classified by GMM.)
mfcc
- 采用MFCC方法提取训练集样本或测试集样本语音特征参数的MATLAB程序，仿真时需先将voicebox语音处理工具箱添加到MATLAB软件中(The MFCC method is used to extract the MATLAB program of the training set sample or the test set sample speech feature parameters. The voicebox voice processing toolbox is added t