搜索资源列表
Based-on-SVM-speaker-recognition
- 基于SVM的文本无关说话人识别算法研究，本文在最后用Matlab程序实现了一个基于支持向量机的说话人识别系统试验平台。并根据对参试者进行的大量身份测试试验，总结系统的各方面性能和分析存在的问题，为进一步研究提供了方向和宝贵的经验。 -SVM-based text independent speaker recognition algorithm, the paper used in the final implementation of a Matlab program based on
SpkTools
- 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别-Speaker recognition can be a part of speech recognition and text-independent speaker recognition
TrainWorld
- 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别 此为训练语音部分-Speaker recognition can be a part of speech recognition and text-independent speaker recognition for this part of the training speech
TrainTarget
- 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别 此为训练说话人模型部分-Speaker recognition can be a part of speech recognition and text-independent speaker identification speaker model in this part of the training
model-for-speaker-verification
- 说话人识别 语音识别的相关书籍 描述了信道补偿算法-Speaker recognition speech recognition books describe the channel compensation algorithm
Speaker-Identification-by-VQ
- 基于矢量量化的说话人识别，希望有人能用的上-Speech/Voice recognition/combine
IS081045
- 描述利用MFCC系数用于说话人识别的过程，包括提取MFCC、MFCC回溯FFT过程-intersession variability in speaker recognition:a behind scene analysis
Speakerrecognitionbased-on-MFCC
- 这是一篇工学硕士论文，主要说关于说话人语音识别，，以支持向量机为分类器，分别以MFCC和IM-FCC为特征单独执行分类，将得到结果按某种方式融合，取两者之长，最后做出判决来提高说话人识别系统的性能。-Speaker recognition is a kind of technology that take the use of the information contained in the speech signal to identify who is the speaker or to
VQ
- 采用MFCC的基于矢量量化的说话人识别，没有语音库，自己建-MFCC+VQ+speaker recognition
basis-of-speech-recognition
- 语音识别的一些基础理论以及语音识别各个组成部分：预处理，参数提取，模式匹配，每个部分有多种详细的方法介绍。还包括说话人识别，语种识别，关键词识别。-basic theory of speech recognition and its component:pre-processing,extraction of parameters,matching.Each section has many method to be supplied.Besides,there are recognition
speaker-recognition
- Brno University Of Technology 大学的2008年NIST说话人识别评测系统介绍。-Brno University Of Technology s speaker recognition system for 2008 NIST evaluation
Speech-recognition
- 运行结果表明该说话人识别系统的识别能力是比较理想的，识别率为88 ，语音库3识别不成功的原因主要有两个，一方面3的录音本身噪音相对大些，导致系统很难识别，另一方面，识别系统的算法还不是很理想，导致识别准确率不是100 。- DISTEU Pairwise Euclidean distances between columns of two matrices Input: x, y: Two matrices whose each column
test1
- 基于高斯混合模型的说话人识别，可以直接运行-Based on gaussian mixture model the speaker recognition
didigtal-image
- 基于GMM的概率神经网络PNN具有良好的泛化能力，快速的学习能力，易于在线更新,并具有统计学的贝叶斯估计理论基础，已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点，还具有许多GMM没有的优点，如强鲁棒性，需要更 -image processing
34617501LPCMCC
- 基于倒谱特征的说话人识别技术 提取语音的倒谱特征进行说话人识别-based Cepstral Speaker voice recognition technology from the Cepstral for Speaker Recognition
svmshiyancx
- 实现基于SVM的说话人识别，其算法比传统的svm有所改进，鲁棒性更强-SVM-based speaker recognition, and improvements in the algorithm than the traditional svm more robust
m
- 基于HMM或者GMM模型的说话人识别系统的实现及改进-Speaker recognition system based on HMM or GMM model and improvement
VQ-GUI
- 基于矢量量化（ＶＱ）的说话人识别，只需输入训练文件夹，即可训练和识别。-Vector quantization (VQ) based speaker recognition, simply enter the training folder, to training and recognition.
wave2mfcc
- 一个非常好的说话人识别特征提取程序，直接对wav文件操作，提取mfcc语音特征值，通过调试-A very good speaker recognition feature extraction process, directly on the wav file, the extraction mfcc voice eigenvalue, through the debugger
gmm_estimate
- gmm模型训练程序，说话人识别系统中基于GMM的说话人识别方法中，对特征参数进行模型训练的函数-gmm model training program, speech recognition system GMM speaker recognition method based on the characteristic parameters of the model training function