vadsohn

Speech PROcessing tools. First edit the makefile to match your needs

用自相关函数提取语音信号基频，提取音频文件的基频等高线(Use the autocorrelation function on segments of the signal (windowsize: 100ms) and compute the fundamental frequency. Use a max_time_lag of 100ms in the autocorrelation function and a window shift of 25ms. Create a fundamental frequency vector and plot the pitch contour.)

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)

实现mffc求解 并且可利用hmm进行孤立词识别(Solving mffc realize and can be used for isolated word recognition hmm)

谱减去，最常用的程序，实习除噪，语音增强(To achieve denoising)

VAD去噪算法，可以有效的过滤静音和无效的语音，同时消除了一些背景噪声。(VAD denoising algorithm, can effectively filter invalid mute and voice, while eliminating some background noise.)

DOA_Estimation,带有详细注释，，包含MUSIC，RootMUSIC，ESPRIT，MVDR，F-SAPES几种算法。(DOA_Estimation, with detailed annotations, contains MUSIC, RootMUSIC, ESPRIT, MVDR, F-SAPES algorithms.)

cubica算法performes ICA by diagonalization of third- and fourth-order cumulants simultaneously(cubica algorithm performes ICA by diagonalization of third- and fourth-order cumulants simultaneously)

一个语音分析程序，包含gammatone滤波器组的分解和重组。对学习语音分析的很有帮助(A speech analysis program contains the gammatone filter group decomposition and reorganization. Helpful learning speech analysis)

求语谱图的matlab程序，非常有用(Spectra for the matlab language program, very useful)