资源列表
matlab-km
- this k-means clustering algorithm codes in matlab, and it is for beginners-this is k-means clustering algorithm codes in matlab, and it is for beginners
pinyin_python
- 能将任一分过词的文章，进行去重、排序，转换为拼音、将拼音转换为音素。可用于汉语语音识别前的语料准备。代码已在python 2.7上运行通过。-Able to any one point of the cross-word article, de-emphasis, sort, convert Pinyin Pinyin conversion to phonemes. Can be used for the corpus preparation before the Chinese speech
Noise_down
- 基于RLS 的麦克风阵列自适应语音降噪 算法及matlab 实现-The method abstracting the desired signal from strong background noise through RLS.
2013-03-05
- 语音采集与处理的第一部分，采集，基于电脑的声卡采集声音数据，这一步个人认为是最重要的-Speech acquisition and processing, collection, based on the computer' s sound card collecting sound data, this step personally think is the most important
Archive
- 分别使用goertzel和fft对dtmf语音信号进行识别-using goertzel algorithm and fft to build a detector separately
genderFormantTracker(matlab)
- 说话人性别识别matlab程序，基音检测、共振峰检测、GMM模型识别-Speaker sex recognition matlab program, pitch detection, formant detection, GMM model identification
HTK
- 国外语音识别软件HTK，具有很强大的功能-The foreign voice recognition software HTK, has very powerful features
qingzhuoyingpinpu
- 实现清音与浊音的频谱分析，通过加不同窗，分析清音和浊音频谱变化-Unvoiced and voiced spectral analysis, analysis of unvoiced and voiced spectral variation, by adding different window
lpc
- 读入一段语音信号，通过自相关法求s的均方预测误差为最小的预测系数-Read into a voice signal s, by the autocorrelation method and the mean square prediction error for the smallest prediction coefficients
lbg
- 实现已知训练序列的矢量量化器（LBG）算法。初始码书从训练序列每隔五个样本选取一组-Achieve a known training sequence of the vector quantizer (LBG) algorithm. The initial codebook from the training sequence every five samples to select a group of
weina
- 自己编写的维纳滤波的算法，有清楚的注释，基于提取初始寂静噪声的滤波算法。-Wiener filtering algorithm, I have written a clear comment the initial silence noise filtering algorithm based on the extraction.
TTS_Demos
- 音响设备接口（SDI）是专为听觉显示，或AUI（音频用户界面），这已被证明是很好的补充GUI（图形用户界面）学术。目前，SDI实现两个Sound对象：语音和听觉符号为例。言语是在3D世界中的定位语音合成相结合的ViaVoice TTS和，A3D一起。在学术上，这种定位可以帮助用户挑选出所需要的信息，两个同时“显示”的声音。这是所谓的“鸡尾酒会效应”。此外，它可以提高存储器中，添加的位置系数对每一个声音。听觉符号为例，从字面上看，可以显示听觉符号为例容易。听觉符号为例是怎么样的音乐modif，图标