搜索资源列表
DTWMFCC
- 这是一个基于动态时间规整的改进的MFCC参数提取程序,用于后续的语音信号的识别,效果较好。-This is a dynamic time warping based MFCC parameters improved extraction procedures for the identification of the subsequent speech signal, better.
SpeakerRecognitionsystem_mfcc
- 说话人识别的一个完整例子,包括分帧、特征提取(MFCC)、分类器(矢量量化VQ),训练阶段和识别阶段分为两个函数,包含样本语音文件,设置好路径,点击main函数即可直接运行。-A complete example of speaker recognition, including framing, feature extraction (MFCC), classification (vector quantization VQ) training phase and recognition ph
voice
- 语音模式识别,基于labview的模式识别,MFCC原理特征提取-Voice pattern recognition, labview-based pattern recognition the MFCC principle feature extraction
CODE
- 提取语音信号的MFCC参数进行语音信号的识别,利用神经网络,自带有训练样本和测试样本-Identification of MFCC parameters of speech signal extraction of speech signal, using neural network, with the training samples and test samples
DTW
- 语音识别的matlab仿真,有文档详细说明,MFCC特征提取,DTW算法识别。对10个简单语音命令进行识别-Speech recognition matlab simulation, documentation detailed descr iption, MFCC feature extraction, DTW algorithm to identify. On 10 simple voice command recognition
SpeechRecAndSyn07
- 一个带用户界面的matlab语音合成和识别的程序,MainGuide01.fig通过提取MFCC,用dtw来计算实时录音和模板之间的最小距离,给出识别结果,并且给出波形图,频谱图,语谱图。MainGuide02.fig是语音合成程序,通过load一个wav文件用LPC,残差和pitch两种方式进行合成,并且能实时听合成语音的效果。-This is an simple user interface program including speech recoginition and speech s
SpeechRecognitionHMM-master
- java实现语音信号的识别,利用MFCC等参数和HMM模型(Java realizes the recognition of speech signals, and utilizes MFCC and other parameters and HMM models.)