搜索资源列表
amis-2.95
- Amis - A maximum entropy estimator 一个最大熵模型统计工具，采用特征进行模型构建-Amis-A maximum entropy estimator a maximum entropy model statistical tools used for model building features
yinacf10
- The Yin algorithm was developed by Alain de Cheveigné of IRCAM-CNRS and Hideki Kawahara of Wakayama University. It allows for real-time continuous (for each sample) fundamental frequency estimation. It features a very low error rate and few tuni
MMSE
- 本程序为经典MMSE方法，引自Y. Ephraim and D.Malah “Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator-Ephraim and D.Malah “Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator
Voice_Pitch_Detection
- 采用自相关法与倒谱法实现语音基音频率检测，将检测到的基音频率以帧为单位画出来。-An Autocorrelation-Based Pitch Estimator,Pitch Detection in the Spectral Domain
fig3_5
- when SNR is high , 1st sample estimator provides good estimate of A. it has no ise effect . so we don’t need averaging effect to reduce noise when SNR is high. However variance is still low in sample mean estimator which shows that in reality ,samp
Laplace
- 传统的短时谱估计语音增强算法通常假设语音谱分量相互独立，没有考虑语音谱分量间的相关性。针对这 一问题，该文提出一种新的基于多元Laplace分布模型的短时谱估计算法。首先，假设语音的离散余弦变换(DCT) 系数服从多元Laplace分布，以此利用谱分量间的相关性；在此基础上，利用多元随机矢量的高斯尺度混合模型表 示，推导得到语音DCT系数矢量的最小均方误差(MMSE)估计的解析表达式；并进一步推导了基于该分布模型的 语音存在概率，对最小均方误差估计子进行修正。实验结果表明，该算法