搜索资源列表
MFCC
- 语音识别中的MFCC算法,用MATLAB实现。-MFCC algorithm with MATLAB.
Voice Discern For STM32F
- 于市售 STM32 开发板上实现特定人语音识别处理项目。识别流程是:预滤波、ADC、分帧、端点检测、预加重、加窗、特征提取、特征匹配。端点检测(VAD)采用短时幅度和短时过零率相结合。检测出有效语音后,根据人耳听觉感知特性,计算每帧语音的 Mel 频率倒谱系数(MFCC)。然后采用动态时间弯折(DTW)算法与特征模板相匹配,最终输出识别结果。先用Matlab对上述算法进行仿真,经数次试验求得算法内所需各系数的最优值。而后将算法移植到 STM32 开发板上,移植过程中根据 STM32 上存储空间相
MFCC
- 基于MATLAB的语音信号MFCC特征参数提取源代码-MFCC feature extraction of speech signal source
MFCC
- 使用MATLAB提取梅尔倒谱系数MFCC特征值-Using MATLAB MFCC feature extraction of Mel-cepstrum coefficient values
MFCC
- 此算法是基于matlab的MFCC特征提取算法,其中包括了分帧、归一化等步骤和代码,非常好用,结果是24维的向量-This algorithm is based on MFCC feature extraction algorithm matlab, including the framing, normalization and other steps and code, very easy to use, the result is 24-dimensional vector
mfcc
- 本MATLAB是用来提取语音信号的MFCC特征,可对.wav文件进行特征提取-The MATLAB is used to extract the MFCC features of speech signals,.Wav files can be extracted
sharks_1.0
- Using MFCC and DPT to identify speech
record
- 语音mfcc,用来录取人声,进行端点检测,分析人声的音量(Voice MFCC, used for voice retrieval, endpoint detection, analysis of voice volume)
Speech recognition using mfcc and lpc
- Speech recognition using mfcc and lpc in matlab
svm
- MATLAB平台提取一段语音信号的mfcc参数(MATLAB mfcc feature extract)
Number Recognition System
- Number Recognition System Using MFCC and Correlation
DigitRecognization
- 矢量量化梅尔倒谱系数孤立词识别,识别说话者声音(speech recognition VQ MFCC)
code 2
- matlab mfcc comparison and calculations
Experiment No.1.pdf
- calculate mfcc and compare features
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)
vad
- mfcc-matlab, speech signal using matlab realize the MFCC feature recognition method
matlab语音识别系统(源代码)
- 基于mfcc参数的语音识别,matlab代码,可以对孤立语音词识别(Speech recognition based on MFCC parameters, matlab code, can identify isolated speech words)
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)
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
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)