资源列表
Lyon_decimation_128
- 语音资料，数字0-9，五个女性每个人读10遍，用于神经网络进行语音识别，供大家使用(Speech Data, Number 0-9, Read 10 times by each of the five women, Used in Neural Networks for Speech Recognition)
谱减法BOLL
- 对基于残留噪声去除的谱减法的编程，实现了高去噪水平(The program of spectral subtraction based on residual noise removal has achieved high denoising level.)
SpeechRec.part
- MATLAB下，采用DTW算法进行语音识别，其中特征参数的提取（MFCC）(MATLAB, DTW algorithm is used to recognize speech, and the extraction of feature parameters (MFCC).)
fixedbeam
- 经典麦克风语音增强算法，当阵元数目越多，语音增强效果越好(Classical microphone speech enhancement algorithm, the more the number of elements, the better the speech enhancement effect)
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
基于动态时间规整（DTW）的孤立字语音识别实验
- 基于动态时间规整（DTW）的孤立字语音识别MATLAB程序(Isolated word speech recognition MATLAB program based on dynamic time warping (DTW))
A-09说明书
- 语音处理模块A-09说明书,模块采用了内置专业声学技术的DSP 单元ATH8809，并配合针对性的算法参数，可提供完善高效的高品质语音传输解决方案。(manual of voice module)
MFCC
- 本程序使用python编写的用于提取mfcc特征(extract feature of MFCC)
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.)
audio_tezheng
- 语音信号的时域、频域与倒谱域分析。 1.分析一帧清音和浊音的自相关函数和倒谱系数 2.用Matlab画出该段语音的时域波形、短时能量、短时平均幅度、短时过零率、短时过电平率 3.选择一帧无声、清音和浊音的语音，用Matlab画出它们的对数幅度谱(Time domain, frequency domain and cepstrum domain analysis of speech signals. 1. Analyze the autocorrelation function and c
beamforming1
- 语音信号处理，阵列为10阵元线阵，宽带和窄带波束形成(Speech signal processing, 10 sensors of microphone linear array,Broadband and narrowband beamforming)
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)