资源列表
I2S
- I2S总线开发相关文档,用于语音开发与应用-I2S bus development of related documents for the development and application of voice
detection
- 基于倒谱，分形，和谱熵的语音端点检测程序，三个文件夹内对应三种程序-Cepstrum-based, fractal, and spectral entropy of speech endpoint detection procedures, the three folders corresponding to the three procedures
HTK-3.4.1
- 非常有用，功能强大的基于隐马尔科夫模型的语音识别工具箱，可在此基础上进行再开发，对于从事语音信号处理的工作人员有很好的参考价值。-Very useful and powerful hidden Markov model based speech recognition toolkit, can be re-developed on this basis, in the speech signal processing for the staff have a good reference val
HTK3.4.1.RAR
- htk3.4.1语音识别工具箱，很好用的-htk3.4.1
lame-3.92-ACM
- lame是公认的转换Mp3的目前最好的工具，本文件包里有lame的说明文件-lame is recognized as the best conversion tool for Mp3 present, this document is the documentation package are lame
formant_extract
- 此压缩包包含语音信号处理中的语音变声代码加音频-The speech signal processing code add audio
speaker_recognition
- 国际上最新的说话人识别算法的源程序，内置语音训练数据-The latest international speaker recognition algorithm source code, built-in voice training data
kalman
- 该程序是卡曼滤波法在语音处理上的应用,能有效的去除噪声,达到语音增强的目的!-The program is Kaman filtering method in the voice processing application, can effectively remove the noise, to achieve the purpose of speech enhancement!
Pitch_extraction_procedures
- 基音提取程序，对于给定一段语音，按一定时间分帧,并从中提取出基音频率-Pitch extraction process, for a given period of voice, according to a certain time-frame, and extracting the pitch frequency
formant_pitch_cepstrum
- 利用倒谱求出语音信号频谱包络和基音频率。-Cepstrum was calculated for the spectrum envelope of speech signal and the pitch frequency.
SpeakerRecognition
- Speaker Recognition by training GMM models for the speakers in the system. Also tells if there s an impostor in the system.
dtw_speech_reco
- 基于DTW的孤立词语音识别，具有很高的识别率，代码为c语言-speech recognition Using DTW