资源列表
Speaker_Speech_Recognition
- this drives a motor based on speaker and speech recognition using mfcc algorithm for speaker recognition and yule walker based power spectrum analysis to perform speech recognition,also uses vqsplit algorithm to reduce data set computation.
LMS
- 实现FIR系统中的最小均方误差自适应滤波算法（LMS）,并通过误差曲面研究其性能。-FIR system in the minimum mean square error adaptive filtering algorithm (LMS), and study its performance through the error surface.
TTS
- 简易文本阅读器，基于SDK5.1，使用C#编程技术。-TTS(text to speech)
SpeechControl
- 语音识别：通过程序员自己编写的语法库进行识别，识别率达到95 以上。-Speech recognition: recognition by programmers write your own syntax library, the recognition rate of over 95 .
monophone
- 针对语音识别数据准备工作，写了一套自动拆分音节为音素的程序，输入一个带拼音的关键词文件，输出一个将音节翻译为音素组合的文件，方便后期语音识别的音素建模。-Preparations for voice recognition data, write a set of automatically split syllable phoneme procedures the Pinyin input with a keyword file, outputs a syllable translation
inial-final
- 在语音识别和语音合成的数据准备阶段，针对音节的 声韵母拆分，写了一套自动拆分音节，输入一个拼音文件，可以输出一个声韵母文件。每一音节都被拆分为对应的声韵母。-Data preparation phase in speech recognition and speech synthesis for a split syllable initials and finals, wrote an automatic split syllables, enter a phonetic file, you
frequency-count-
- 针对语音识别中语音数据库 设计，在音节 音素 声韵母等单元建模之前，需要考虑某些音节或音素或声韵母出现的频率，该程序可以很方便统计某些音节或音素或声韵母出现的频率，也可以在此基础上修改下代码，实现某些音节或音素出现在某个位置的频率，有利于语音识别 语音合成的数据工作。-Database designed for speech recognition in voice, syllables and phonemes sound vowels unit modeling before, need t
mfcc-feature-extraction
- 针对语音识别中MFCC特征提取，从HTK3.4.1版本中抽出MFCC提取模块，可以单独运行，对一批wav录音文件进行MFCC特征提取，一个wav文件对应一个特征文件。并且备有详细的注释，有利于语音识别初学者学习使用。-MFCC extraction module extracted from HTK3.4.1 version for speech recognition MFCC feature extraction, can be run separately, MFCC feature ex
qinghuaci
- 用matlab软件演义青花瓷曲调周杰伦的歌曲很好听不信你-The matlab software Kingdoms blue and white porcelain tunes
cis-matlab
- cis算法是人工耳蜗声音处理的核心算法，用于将语音信号进行频带分解以及合成。-cis algorithm is the core of the cochlear sound processing algorithms for voice signal band decomposition and synthetic.
DTMF4
- 试验DTMF软解码，这个一个vb写的实验性质的解码程序，可以生成dtmf音和解码。-Test DTMF soft decoding, this is a vb write the experimental nature of the decoding process can be generated dtmf tone and decoding.
DTMF3
- DTMF(双音多频）检测程序，就是目前PSTN电话中的来电显示的-DTMF (dual-tone multi-frequency) testing procedures, is the current PSTN phone calls stuff