Description: 武汉大学的研究生论文,关于用DSP5402实现说话人识别的论文.算法采用DTW并进行了改进-Wuhan University graduate thesis on the use of DSP5402 Speaker Recognition realize papers. DTW algorithm and improved Platform: |
Size: 3034112 |
Author:叶小勇 |
Hits:
Description: 说话人识别方法及其系统的应用开发研究.毕业设计论文,详细.本文对说话人识别方法应用作了较深入系统的研究。采用的方法分别是矢量量化(VQ)识别方法、隐马尔可夫模型(HMM)识别方法、高斯混合模型(GMM)识别方法。-Speaker Recognition Method and system development and research. Graduate design thesis in detail. In this paper, methods of application of speaker recognition system were made more in-depth research. Methods used are vector quantization (VQ) identification methods, hidden Markov model (HMM) to identify methods, Gaussian mixture model (GMM) identification methods. Platform: |
Size: 623616 |
Author:叶小勇 |
Hits:
Description: 说话人识别的matlab代码，效果还行,凑合用吧-Speaker Recognition matlab code, the effect also visit improvise with it Platform: |
Size: 640000 |
Author:张成 |
Hits:
Description: 基于小波神经网络PNN 的说话人识别程序，希望对大家有所帮助-Based on Wavelet Neural Network PNN the speaker recognition process, and they hope to help everyone Platform: |
Size: 7168 |
Author:张杰 |
Hits:
Description: 通过分析语音特征参数的特点和说话人识别的基本方法，利用 DSP的硬件平台，以线性预测倒谱系数为
特征参数提取算法以及 隐马尔可夫模型为建模算 法，实现 电子语音锁 的系统设 计。实验 结果表 明系统在 内部模 型
数小于 1O时识别精度高 ，达到 安全保 密的要求。 -By analyzing the characteristic parameters of voice characteristics and speaker recognition, the basic methods, the use of DSP hardware platform, linear prediction cepstral coefficients for feature extraction algorithms and Hidden Markov Model for modeling algorithms, electronic voice-lock system设计. The experimental results show that the internal model system in less than 1O identification accuracy when, reaching the security and confidentiality requirements. Platform: |
Size: 195584 |
Author:niu xiaolei |
Hits:
Description: 说话人识别中，采用MFCC_D时的主程序，同样包括提取，训练，识别三步。-Speaker Recognition using MFCC_D when the main program, also including the extraction, training, identification of three steps. Platform: |
Size: 8192 |
Author:santa q |
Hits:
Description: 在做和语音信号处理相关的项目时要用到的语音工具箱,比如语音识别,说话人识别等,里面有一些已经封装好的小函数,可供大家编程序的时候直接调用-In speech signal processing to do and projects related to voice use toolbox, such as speech recognition, speaker recognition, etc., there are some good small function package for everyone when programmed direct call Platform: |
Size: 143360 |
Author:frieda |
Hits:
Description: 数字的语音识别matlab程序
训练及识别数据太大,少量上传一点,大家可以用COOLEDIT等软件仿照自己制作.(*.wav文件采样率8000,单声道,采样精度16位,16bit Motorola PCM,*.lab文件存的是语音的起止点和语音内容). -Digit speech recognition matlab program too much training and recognition data, a small amount of upload that you can use software such as CoolEdit modeled to produce their own. (*. Wav file sampling rate 8000, mono, 16-bit sampling precision, 16bit Motorola PCM,*. lab files maintained by the beginning and ending points of speech and voice content). Platform: |
Size: 314368 |
Author:er |
Hits:
Description: 说话人识别和训练系统所用的很多源码，内容很详实，希望大家能用的上-Speaker Recognition and training system used by a lot of source code, content is very informative and hope that we can use the upper Platform: |
Size: 8192 |
Author:姜海鹏 |
Hits:
Description: 一个跟说话人识别相关的资料，非常适合入门，精彩不容错过呀-A speaker recognition with the relevant information is well suited to introduce the best of me not to be missed Platform: |
Size: 124928 |
Author:欧阳 |
Hits:
Description: Wavelet Subband coding for speaker recognition
The fn will calculated subband energes as given in the att tech paper of ruhi sarikaya and others. the fn also calculates the DCT part. using this fn and other algo for pattern classification(VQ,GMM) speaker identification could be achived. the progress in extraction is also indicated by progress bar.-Wavelet Subband coding for speaker recognitionThe fn will calculated subband energes as given in the att tech paper of ruhi sarikaya and others. The fn also calculates the DCT part. Using this fn and other algo for pattern classification (VQ, GMM) speaker identification could be achived. the progress in extraction is also indicated by progress bar. Platform: |
Size: 88064 |
Author:chan man man |
Hits:
Description: 高斯混合模型[Gaussian mixture model,简称GMM]是单一高斯机率密度函数的延伸,由於GMM 能够平滑地近似任意形状的密度分布,因此近年来常被用在语音与语者辨识,得到不错的效果。 -Gaussian mixture model [Gaussian mixture model, referred to as GMM] are single-Gaussian probability density function of the extension.GMM can approximate arbitrary smooth shape of the density distribution, so it is often used in speech and speaker recognition in recent years. Platform: |
Size: 63488 |
Author:杨清山 |
Hits:
Search - speaker recognition