资源列表
echo
- speex自带的回音消除源码,听说很不错,传上来共享下-speex echo cancellation comes with source code, I heard a very good pass up to share the
PAPR-in-OFDM
- 基于语音保留的剪裁引导噪声和复杂的基带活性集的性能分析,降低OFDM系统中的平均峰均功率比。-Performance Analysis of Clipping Noise Guided and Complex Base-Band Active-Set methods Based on Tone Reservation for PAPR Reduction in OFDM Systems
chen
- 通过语音识别来实现你所需要的操作,多用于多媒体展览展示项目。在此原代码的基础上能够通过改写来制作其他多媒体应用软件。-Achieved through voice recognition operation you need, and more for multimedia exhibition project. In the original code, based on the rewrite to make through other multimedia applications.
mynewlms5
- 基于matlab的LMS算法的自适应滤波器-Matlab-based adaptive filter LMS algorithm
mfccOfSoundmethodand
- 语音特征pdf资料,关于发音方法,发音部位的mfcc特征提取,稍微细节的思路-Pdf speech features information on pronunciation, articulation of mfcc feature extraction, the idea of a little detail
VQ
- 采用MFCC的基于矢量量化的说话人识别,没有语音库,自己建-MFCC+VQ+speaker recognition
11
- 语音朗读,可以朗读文字。但是在使用时要联网-Speech in English
htkbook.ps
- 声音识别,声音匹配,建模,自动生成lrc、srt-Voice recognition, voice matching, modeling, automatic generation of lrc, srt
SSP-Toolkit
- sound toolkit fft, cepstrum, dtw recognition
MFCC1
- MFCC program, mel frequency cepstral coeficient
WavReadandWrite
- wavreadandwrite实现wav文件的读取与写入,适合语音处理只用-wavreadandwrite achieve read and write wav files for voice processing only
ms_slp
- 个基于DTW的的孤立词的语音识别系统,采用率为800,可以识别六个字左右的短语,-rwer werwe