资源列表
endPointDetect
- 简单的基于门限值的语音端点检测。先将数字化的语音信号封装成帧,利用最大的帧幅值乘以一个比例因子得到门限值-Simple threshold-based voice end point detection. First,framing the digital voice signal , then using the maximum amplitude to multiply a frame scale factor to get threshold
jinbao.m
- 基于自适应子带频谱熵的稳健性语音端点检测
qiaodu
- 基于峭度的独立分量分析,包括并行提取和串行提取的程序-ICA based on kurtosis analysis, including parallel and serial extraction procedures for extracting
getparam
- 在基于hmm的语音识别中计算前向概率,后向概率以及各种参数结构的源代码。-based on voice recognition to the calculation of the probability that after the probability of various parameters of the structure of the source code.
CirclePrintCorr_wo
- 剥波自相关法基音检测,用于检测“我和泥巴无语”音-Stripping wave autocorrelation pitch detection method for detecting " I am silent and mud" sound
lsm_blind_equilibria_godard_1
- 上述程序是基于LMS自适应算法的blind_equilibria_godard盲均衡算法。-above procedure is based on the LMS adaptive algorithm blind_equilibria_god ard blind equalization algorithm.
hmm_g
- 隐马尔科夫模型的建立,该模型可广泛应用于语音识别、对象定位、多序列比对中。
zikongjian
- 该程序是基于子空间的语音去噪声,该方法使用广泛,能取得很好的语音增强效果!-The program is based on the sub-space of the voice to noise, the method widely used and can achieve very good speech enhancement effect!
NT_LMS
- 这是一个神经网络LMS算法,对于初学圣经网络的网民非常有用。-This is a neural network LMS algorithm, for a novice Bible network of netizens very useful.
voiceanalasis
- 运用matlab工具对语音信号处理的几个方面:短时能量、端点检测、和功率谱及短时傅立叶变换特性作了简单的分析。-use Matlab tool for voice signal processing areas : short-term energy and endpoint detection, and the power spectrum and the characteristics of short-time Fourier transform with a simple analysi
mfccvc
- 利用DELPHI实现的语音识别过程中MFCC特征提取的程序,每帧提取20个MFCC系数-use of voice recognition process MFCC feature extraction procedures, Each frame extraction coefficient of 20 MFCC
mp3read
- 读mp3文件格式的matlab 源程序