搜索资源列表
speakerrecognition
- 说话人身份识别程序,采用MFCC参数提取,并建立GMM模型来进行识别-Speaker identification procedures, using MFCC extraction, and the establishment of GMM model to identify
VQ-pattern-recognition
- VQ声纹识别算法和实验. 摘要:采用线性预测倒谱系数(1inear prediction cepstrum coefficient,LPCC)作为语音的特征参数,矢量量化(vector quantity,VQ)方法进行模式匹配,探讨声纹识别以实现身份认证,并对此识别方法进行了相关的实验.通过验证,这种方法可以区分不同的说话人,并且在做说话人辨认实验时可达到较高的识别率.-VQ pattern recognition algorithms and experimental sound. Ab
mfccyuyinshibie
- 采用不同样本进行语音特征提取,来实现不同说话人身份的识别-Different samples of voice feature extraction to achieve recognition of different identities speaker
vq-Speakerrecognized
- vq矢量量化,对说话人进行识别,内置有语音样本,识别率高达90 。对语音信号进行读取,预处理,特征参数提取,向量量,训练,对比识别。-vq vector quantization for speaker identification, built-in voice samples, the recognition rate of 90 . Read the speech signal, preprocessing, feature extraction, the amount of vector
3D-convolutional-speaker-recognition-master
- 使用3d卷积神经网络对说话人身份进行识别(Using 3D Convolutional Neural Networks for Speaker Verification)
matlab程序代码
- 所有说话人均已经训练,若想重新训练,可删除数据后重新训练,也可知删除部分人的数据。(All speaking people have been trained. If we want to retrain, we can delete data and retrain. We can also delete data from some people.)