资源列表
l401
- 语音程序，自动朗读“大家好”，对于speech sdk的初学者是个好实例。-Voice procedures, automatic reading " Hello, everyone, for speech sdk beginners is a good instance.
mfcc-complet
- The algorithm divides the speech sample into fames and then computes mfcc of each frame and stores in the matrix
bp(1)
- 车牌识别，虽然不太成熟，请大神们指导。谢谢帮忙-License plate recognition, although less mature, the Great God who guides
dtw
- 外国人写的Derivative Dynamic Time Warping相关内容，对理解dtw算法有帮助-Written by foreigners of the Derivative Dynamic Time Warping related content to help understand dtw algorithm
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
the-awe-and-mystery-of-T-Norm_eurospeech03_tnorm.
- about test normalization(t-norm) which is applicable for speaker verification score normalization
SVMSVM-SUPPORT-VECTOR-MACHINE-SPEAKER-VERIFICATIO
- SVM for speaker verification
hg
- 基于HMM的姿势识别，matlab编写，希望对大家有用-HMM based hand gesture recognition，matlab
Bayeslilun
- 贝叶斯决策理论方法是统计模式识别的一个基本方法，类概率密度已知和类别数已知-Bayesian decision theory method of statistical pattern recognition is a basic method, the class probability density known and category known number
tu-xiang
- 盲源分离 读取语音文件并显示其频谱图像 基于声场景分析的混叠语音分离研究-Blind Source Separation the aliasing voice read the voice file and display its spectrum image based on the acoustic scene analysis Separation
video
- 智能视频监控中目标检测与识别，电子版图书，绝版书，算法类，万卫兵 -video suriverince
Kalmanflt
- filter for denoising noisy speech (corrupted by white noise). Kalman filtering of noisy speech usually have two steps: Estimating the AR parameters of speech segment