ToolboxBSS

基于动态时间规整与隐马尔科夫模型的自动语音识别系统(Automatic speech recognition system based on dynamic time warping and hidden Markov model)

通过语音分帧、端点检测、pitch提取、DTW算法，实现歌曲识别(Through voice framing, endpoint detection, pit extraction, DTW algorithm, song recognition is realized)

用vq算法进行说话人识别，能达到良好的效果(Using VQ speaker recognition algorithm can achieve good results)

基于熵的端点检测算法，比传统的端点检测能更精确的检测出端点(endpoint detection algorithm than the traditional endpoint detection more accurate detection of Endpoint)

国外著名的语音合成开发教程。英文的，原汁原味。(famous speech synthesis Development Guide. English, what is genuine.)

分段信噪比测试，主要是用于语音增强，语音编码后的测试使用(segment SNR test, primarily for speech enhancement, speech coding after testing)

基于负熵的盲源分离算法，可以用于语音的盲分离，提高语音信号质量(Negative entropy algorithm based on blind source separation, can be used to blind separation of speech, improve the quality of voice signal)

这是基于隐马尔可夫模型的连续语音识别代码，不同于dtw,这是个完整的工程，我把需要的voicebox也放进去了，一共用到9个子函数，包括模板的训练算法何识别算法，是完全可以使用的。(This is based on the hidden Markov model of continuous voice recognition code, different the dtw, which is a complete project, I need to put the voicebox into a total of nine sub-functions, including the template training algorithm to identify the algorithm, Is fully available.)

G711标准的语音编解码算法。以便于对语音信号进行大量存储(speech coding)

基于倒谱短时部分反映了语音的声道特性，先用汉明窗取一帧语音，然后经变换得到语音倒谱，将倒谱短时部分取出，进行正交反变换后将得到声道的对数谱，即得到语音频谱的包络。将频谱包络和频谱画在一张图上，有很好的对比效果。获取的包络效果十分好。(Based Cepstral partly reflects the short channel characteristics of the speech, first take a Hamming window with a frame of speech, and speech cepstrum obtained by converting the cepstrum short segment out inverse orthogonal transform to obtain channel will of the spectrum, i.e. to obtain the envelope of the speech spectrum. The spectral envelope and spectral painted on a chart, there is a good contrast. Get the envelope effect is very good.)