资源列表
melmfcc
- 从说话人的语音信号中提取说话人的个性特征是声纹识别的关键。主要介绍语音信号特征提取方法中的Mel倒谱系数 -From the speaker s voice signal to extract the speaker s personality traits is the key to Voiceprint identification. Mainly introduces the speech signal feature extraction method in Mel cepstral
yybs.tgz
- delphi写的语音报时器
lpc222
- 这是一个语音识别系统的代码。所用到的方法是线性预测法，基于音节激励和声音信号激励的-This is a rcode about speech identification and the methods used is Linear predictive coding(both Pitch and voiced excited)
IEEEXplore6
- how to recognize the emotion using hmm technique.
mpsound
- 录制一段个人自己的语音信号。对录制的信号进行采样；画出采样后语音信号的时域波形和频谱图；对语音信号进行加噪和去噪处理，画出滤波后信号的时域波形和频谱，并对滤波前后的信号进行对比，分析信号的变化；回放语音信号；实现快录慢放、慢录快放等功能。-Record a person' s own voice signal. Of the recorded signal sampling draw sample after the speech signal time-domain waveform
Comparison
- 该论文利用中文语音，对Sphinx和HTK进行了对比，通过对比实验有效说明两者的特点。-To compare Sphinx and HTK.
lpc2
- 语音压缩中的线性预测编码技术,对大家开发语音识别与合成会有很大的帮助。-Voice compression in the linear predictive coding technique, we develop speech recognition and synthesis will be of great help.
paper_about_ICA
- 基于快速ICA的混合语音信号分离.pdf-Based on Fast ICA mixed voice signal separation. Pdf
fsatica
- fastica的混合语音分离，研究生论文。-fastica mixed voice separation, post-graduate dissertations.
voice-frequency
- 提取声音基频，对于语音识别和语音频谱分析提供一定便利-Extraction voice frequency
Speech-analysis-and-synthesis-3-FilterBank
- Speech analysis and synthesis-3 FilterBank