资源列表
gmm_creation_mle
- 采用期望最大算法最优化初始高斯混合模型的程序，笔者借用ubm自适应方法，很好的解决了模型不收敛的问题。-expectations largest algorithm using optimization initial Gaussian mixture model procedures, the author borrowed ubm adaptive method, a good model is not the solution convergence problem.
non negative matrix factorization
- non negative matrix factorization for audio source seperation
AVT
- java avt播放程序，可移植到lunix下运行-java avt player can be transplanted to run lunix
omlsa.m.tar
- 基于IMCRA单通道噪声估计,基于Omlsa(optimally-modified log-spectral amplitude)语音增强-Isreal Cohen- omlsa : Single Channel OM-LSA with IMCRA noise estimator. Noise psd estimation & Speech enhencement
CD-Player
- The Example of the simple player CD Player.
mld_from_m68k_asm
- sample core to generate mld audio files from m68k asm sources. mld format is a ring music format for docomo mobile phones. this sample code includes useful macro file.
avq_dec
- 利用c语言实现的PEAQ程序，且已经调试可用。-a c proguamme for PEAQ using c language.
fft-v1.0.0.40.tar
- fft的快速实现，核心部分无任何耗时的sin,cos运算，所需要的数据初始化时全部已经计算好了。并且提供了fft的定点代码（这是很多fft不具有的），可以方便地移植到嵌入式和DSP环境-fft of rapid implementation, the core portion without any time-consuming sin cos operation, the initialization of the data needed all been calculated. And pr
Solar-energy-and-photovoltaic-power-generation.ra
- Solar energy and photovoltaic power generation
resampling
- audio watermarking extract
音调F0检测 javascript版本
- 采用自相关算法进行基频检测，对于乐音一般效果还可以