资源列表
lsp3
- 语音信号处理的最基本的Maylab处理程序，包括读入语音波形，清音浊音的检测，加窗，过零率，短时能量，基音最大值。最后有test给出演示-speech signal processing Maylab the most basic procedures, including reading the speech waveform. voiceless voiced detection, adding windows, the zero-rate, short-term energy, the m
fftw3_3.1.2.orig.tar
- fft运算的类库。方便调用。是在linux下编译的。-fft library operations. Call convenience. In the compiler under linux.
phoneme
- 音素分割.很实用.基于SAPI.肯定不会让大家失望-phoneme segmentation. Practical. Based on SAPI. Definitely not let you down
lpc_specgram
- 基于MATLAB语音线性预测分析报告及程序实现和语谱图实现。-linear prediction analysis and procedures to achieve and realize Spectrogram.
FastOutofvocabularyRejectionlgorithm
- 针对语音识别的实时性要求提出了一种新的基于支持向量机的OOV快速拒识算法并将其应用于基于DSP 实现的孤立词语音识别系统中。-Speech Recognition real-time requirements of a new support vector machines based on the vocabulary rapid rejection algorithm which can be used for the DSP-based Isolated Speech Recognitio
dtw_revised
- 利用DTW模版匹配算法实现0~9十个数字的识别。-use DTW template matching algorithm 0-9 10-digit identification.
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
DRAWdelphi
- 利用DELPHI语言实现语音信号的语谱图显示-use Delphi language voice signal spectra show that the language
fftw-3.1.2-dll
- fft运算的函数库。使用方便。linux下编译。-fft operations functions. Easy to use. Compiling under linux.
spectrumsub
- 在matlab开发环境下的谱减法算法，主要用在了作者的语音增强算法当中。-in Matlab development environment spectral subtraction algorithm, which was spent mainly on the author's speech enhancement algorithm.
speech_noise_creat
- 将多种噪声与纯净语音合成的算法，用于作者在论文中的带噪语音来源-diversified pure noise and speech synthesis algorithm, the authors of the papers for the sources of Noisy Speech
LSAgai
- 对数谱最小均方误差语音增强算法（LSA-MMSE），对加入有音无音判决进一步提高信噪比，消噪效果非常好。适合各种平稳噪声。-right spectrum minimum mean square error speech enhancement algorithm (LSA - MMSE). sound right to a sound judgment without further improve signal-to-noise ratio, denoising effect was very