matlab工具voicebox函数中文说明

需要自己去下载文件解压到toolbox里面并设置路径方可使用

加载链接http://blog.csdn.net/cwfjimogudan/article/details/45129947

Voicebox:在matlab使用的语音程序工具

  一些文件使用加前缀"v_"避免命名冲突

 

  音频文件输入或输出 

    readwav       - 读取WAV文件

    writewav      - 写WAV文件

    readhtk       - 读 HTK waveform文件

    writehtk      - 写 HTK waveform 文件

    readsfs       - 读 SFS文件

    readsph       - 读 SPHERE/TIMIT waveform 文件

    readaif       - 读 AIFF Audio Interchange file format 文件

    readcnx       - 读 BT Connex database 文件

    readau        - 读 AU文件(from SUN)

    readflac      -读 FLAC 文件

 

  频率尺度转换

    frq2bark      - Convert Hz to the Bark frequency scale利用基本频率hz转换到Bark频率尺度

    frq2cent      - Convert Hertz to cents scale利用基本频率hz转换到cents尺度

    frq2erb       - Convert Hertz to erb rate scale利用基本频率hz转换到erb比例尺度

    frq2mel       - Convert Hertz to mel scale利用基本频率hz转换到梅尔尺度

    frq2midi      - Convert Hertz to midi scale of semitones利用基本频率hz转换到MIDI文件音高

    bark2frq      - Convert the Bark frequency scale to Hz 利用Bark频率尺度转换到基本频率hz

    cent2frq      - Convert cents scale to Hertz利用cents尺度转换到基本频率hz

    erb2frq       - Convert erb rate scale to Hertz利用erb比尺度转换到基本频率hz

    mel2frq       - Convert mel scale to Hertz利用梅尔尺度转换高基本频率hz

    midi2frq      - Convert midi scale of semitones to Hertz利用midi文件音高转换到基本频率hz

 

 

傅里叶Fourier/离散余弦DCT/离散哈脱莱Hartley 变换 

    rfft          - FFT of real data实数的傅里叶变换

    irfft         - Inverse of FFT of real data实数的反傅里叶变换

    rsfft         - FFT of real symmetric data实对称数据的傅里叶变换

    rdct          - DCT of real data实数的离散余弦变换

    irdct         - Inverse of DCT of real data实数的反离散余弦变换

    rhartley      - Hartley transform of real data实数的离散哈脱莱变换

    zoomfft       - calculate the fft over a portion of the spectrum with any resolution任意分辨率的频谱傅里叶计算变换

    sphrharm      - calculate forward and inverse shperical harmonic transformations正向和反向球面谐波计算变换

 

  Probability Distributions概率分布

    berk2prob     - Convert Berksons to probability利用berk转换到probability概率

    gaussmix      - Fit a gaussian mixture model to data values拟合高斯混合模型的数据

    gaussmixd     - Calculate marginal and conditional density distributions and perform inference边际和条件密度推挤计算

    gaussmixk     - Estimate Kuleck-Leibler divergence between two GMMs两个高斯混合模型交叉熵散度估测

    gaussmixg     - Calculate global mean, covariance and mode of a Gaussian mixture高斯混合的全均值，协方差，模态计算

    gaussmixm     - Estimate mean and variance of GMM vector magnitude高斯混合模型向量幅度均值、方差估计

    gaussmixp     - Calculates and plots full and marginal probability density from a GMM高斯混合模型边缘概率密度的计算和绘制

    gaussmixt     - multiplies two GMMs together两个高斯混合模型相乘

    gausprod      - Calculate the product of multiple gaussians多个高斯结果的计算

    gmmlpdf       - OBSOLETE - use gaussmixp instead过时，使用gussmixp代替此函数

    histndim      - N-dimensional histogram (+ plot 2-D histogram)N维直方图（+绘制二维直方图）

    lognmpdf      - Prob density function of a lognormal distribution对数正态概率密度函数

    maxgauss      - Calculate the mean and variance of max(x) where x is a gaussian vector一个高斯向量均值或方差的最大值计算

    normcdflog    - Calculate the log of the Normal cdf without underflow没有下溢的正常CDF日志文件计算

    prob2berk     - Convert probability to Berksons利用probability概率转到berk

    randvec       - Generate random vectors产生随机向量

    randiscr      - Generate discrete random values with prescribed probabilities生成规定概率的离散随机值

    rnsubset      - Select a random subset选择的一个随机子集

    randfilt      - Generate filtered random noise without transients产生无瞬变的滤波随机噪声

    stdspectrum   - Generate standard audio and speech spectra生成标准音频和语音谱

    usasi         - Generate USASI noise (obsolete: use stdspectrum instead)过时，用stdspectrum函数代替

    v_chimv       - Approximate mean and variance of non-central chi distribution非中心分布的近似均值和方差

    vonmisespdf   - Calculate the pdf of the Von Mises (circular normal) distribution计算米塞斯分布（循环正常）的pdf

 

  Vector Distances向量距离

    disteusq      - Calculate euclidean/mahanalobis distances between two sets of vectors两个向量集合的欧式距离和马氏距离

    distchar      - COSH spectral distance between AR coefficient sets AR系数集之间的双曲余弦谱距离

    distitar      - Itakura spectral distance between AR coefficient sets AR系数集之间的Itakura谱距离

    distisar      - Itakura-Saito spectral distance between AR coefficient sets AR系数集之间的ltakura-Saito 谱距离

    distchpf      - COSH spectral distance between power spectra 功率谱间的双曲余弦谱距离

    distitpf      - Itakura spectral distance between power spectra 功率谱间的ltakura谱距离

    distispf      - Itakura-Saito spectral distance between power spectra 功率谱间的ltakura-saito谱距离

 

  Speech Analysis语音分析

    activlev      - Calculate the active level of speech (ITU-T P.56)估算语音的活跃程度

    activlevg     - Calculate the active level of speech robustly to added noise估算语音有力的加性噪声活跃程度

    dypsa         - Estimate glottal closure instants from a speech waveform语音波形声门闭合时刻估计

    enframe       - Divide a speech signal into frames for frame-based processing语音信号分成基于帧的分帧处理

    correlogram   - calculate a 3-D correlogram三维相关图计算

    ewgrpdel      - Energy-weighted group delay waveform延迟波形的能量给加权

    fram2wav      - Interpolate frame-based values to a waveform波形中插入帧值

    filtbankm     - Transformation matrix for a linear/mel/erb/bark-spaced filterbank from dft output 线性/梅尔/erb/bark-spaced滤波器组转换矩阵从偏流输出

    fxpefac       - PEFAC pitch tracker pefac基音跟踪

    fxrapt        - RAPT pitch tracker       rapt（图像？）基音跟踪

    gammabank     - Calculate a bank of IIR gammatone filters     IIRgammabakn滤波器计算

    importsii     - Calculate the SII importance function (ANSI S3.5-1997)SII重要函数计算

    modspect      - Caluclate the modulation specrogram  调制specrogram计算

    mos2pesq      - Convert MOS values to equivalent PESQ scores   MOS值等效转换到PESQ得分

    overlapadd    - Reconstitute an output waveform after frame-based processing重建一个基于帧处理后的输出波形

    pesq2mos      - Convert PESQ scores to equivalent MOS values  PESQ得分等效转换到MOS值

    phon2sone     - Convert signal levels from phons to sones信号电平从phons转换到sones

    psycdigit     - Experimental estimation of monotonic/unimodal psychometric function using TIDIGITS单调/单峰心理功能使用TIDIGITS实验估计

    psycest       - Experimental estimation of monotonic psychometric function单调心理功能函数实验估计

    psycestu      - Experimental estimation of unimodal psychometric function 单峰心理功能函数实验估计

    psychofunc    - Psychometric functions心理功能

    v_sigma       - Identify glottal closure and opening intstants from Lx or EGG waveform利用Lx或蛋波形识别声门的开闭

    snrseg        - Segmental SNR and Global SNR calculation分段信噪比和全信噪比计算

    sone2phon     - Convert signal levels from sones to phons信号电平sones转换到phons

    soundspeed    - Returns the speed of sound in air as a function of temperature返回声音在空气的速度于温度变化的函数

    spgrambw      - Spectrogram with many options声谱图的许多选项

    stoi2prob     - Convert STOI intelligibility measure to probability of correct recognition标准清晰度测量转换到正确识别概率

    txalign       - Align two sets of time markers两套时间标记集对齐

    vadsohn       - Voice activity detector语音活动侦测器

    v_ppmvu       - Calculate the PPM, VU or EBU levels of a signal计算信号的PPM、VU、EBU水平

 

  LPC Analysis of Speech 语音线性功能控制器LPC分析

    ccwarpf       - warp complex cepstrum coefficients复倒谱系数的变形

    lpcauto       - LPC analysis: autocorrelation method LPC分析 自相关法

    lpcbwexp      - Bandwidth expansion of LPC filter LPC滤波器的带宽扩展

    lpccovar      - LPC analysis: covariance method LPC分析 协方差分析

    lpcconv       - Arbitrary conversion between LPC representations LPC表示的任意转换

    lpcifilt      - inverse filter a speech signal语音信号的逆滤波器

    lpcrand       - create random stable filters创建随机稳定的滤波器

    lpcrr2am      - Matrix with all LPC filters up to order p矩阵用LPC滤波器到p阶

    lpcstable     - check for stability and force stable filters稳定滤波器的稳定和力量检查

    lpc--2--      - Convert between alternative LPC representation替代LPC表示的转换

 

  Speech Synthesis语音合成

    sapisynth     - Text-to-speech synthesis of a string or matrix 字符串的文本或矩阵到语音的合成

    glotros       - Rosenberg model of glottal waveform声门波形的罗森堡模型

    glotlf        - Liljencrants-Fant model of glottal waveform声门波形到liljencrants-Fant模型

 

  Speech Enhancement语音增强

    estnoiseg     - Estimate the noise spectrum from noisy speech using MMSE method利用最小均方差MMSE方法从噪音中估算噪声频谱

    estnoisem     - Estimate the noise spectrum from noisy speech using minimum statistics利用最小统计从噪音中估算噪声频谱

    specsub       - Speech enhancement using spectral subtraction采用谱减法增强语音

    ssubmmse      - Speech enhancement using MMSE estimate of spectral amplitude or log amplitude采用MMSE估计谐振幅或对数振幅增强语音

    ssubmmsev     - Speech enhancement using MMSE estimate and VAD-based noise estimation利用最小均方法估计法和基于VAD的噪声估计法增强语音

    specsubm      - (obsolete algorithm) Spectral subtraction 过时。谱减法

    spendred      - Speech Enhancement and Dereverberation (Doire's algorithm)语音增强和混响（doir算法）

 

  Speech Coding语音编码

    lin2pcmu      - Convert linear PCM to mu-law PCM线性PCM转换到μ律PCM

    pcma2lin      - Convert A-law PCM to linear PCM A律PCM转换到性PCM

    pcmu2lin      - Convert mu-law PCM to linear PCM μ律PCM转换到线性PCM

    lin2pcma      - Convert linear PCM to A-law PCM A律PCM转换到线性PCM

    kmeanlbg      - Vector quantisation: LBG algorithm矢量量化  LBG算法

    kmeanhar      - Vector quantization: K-harmonic means矢量量化 调和平均算法

    potsband      - Create telephone bandwidth filter电话带宽过滤器创建

    v_kmeans      - Vector quantisation: k-means algorithm矢量化 k均值聚类算法

 

  Speech Recognition语音识别

    melbankm      - Mel filterbank transformation matrix梅尔滤波器组变换矩阵

    melcepst      - Mel cepstrum frontend for recogniser梅尔倒频谱前端识别

    cep2pow       - Convert mel cepstram means & variances to power domain利用梅尔倒频谱均值和方差转换到功率域

    pow2cep       - Convert power domain means & variances to mel cepstrum利用功率域转换到梅尔倒频谱均值和方差

    ldatrace      - constrained Linear Discriminant Analysis to maximize trace(W\B)约束线性分析到最大限度跟踪

 

  Signal Processing信号处理

    ditherq       - Add dither and quantize a signal信号加抖动和量化（颤音？我自己猜想的）

    filterbank    - Apply a bank of IIR filters to a signal对信号应用IIR过滤器

    maxfilt       - Running maximum filter运行的最大值过滤器

    meansqtf      - Output power of a filter with white noise input带有白噪声输入的波滤器的的功率输出

    momfilt       - Generate running moments生成运行时刻

    schmitt       - Pass a signal through a schmitt trigger信号通过施密特触发器

    sigalign      - Align a clean refeence with a noisy signal对齐一个带有噪声信号的干净refeence

    teager        - Calculate the Teager energy waveform Teager能量波形计算

    v_addnoise    - Add noise to a signal at a chosen SNR 给信号加一个选择好的信噪比的噪声

    v_findpeaks   - Find peaks in a signal or spectrum在一个信号或谱中找到峰

    v_resample    - Resamples a signal: identical to MATLAB resample but removes filter transients重采样信号 和matlab自带重采样相同，但消除滤波器瞬变

    v_windinfo    - Calculate window properties and figures of merit窗口性能和数字优点计算

    v_windows     - Window function generation窗函数生成

    zerocros      - Find interpolated zero crossings查找插值零点（零点）用buffer分片以后的波形数据可以作为输入参数，返回是波形数据的y=0时线性求的x点集合。（点处斜率正zerocros(y,'p') 负 zerocros(y,'n')  默认全部或者'b'）

 

  Information Theory信息理论

    huffman       - Generate Huffman code 生成哈夫曼编码

    entropy       - Calculate entropy and conditional entropy熵和条件熵的计算

 

  Computer Vision文本计算

    imagehomog    - Apply a homography transformation to an image with bilinear interpolation双性线插值图像的单应变换应用

    polygonarea   - Calculate the area of a polygon多边形面积计算

    polygonwind   - Test if points are inside or outside a polygon测试点在多边形的内部或外部

    polygonxline  - Find where a line crosses a polygon

    qrabs         - Absolute value of a real quaternion

    qrdivide      - divide two real quaternions (or invert one)

    qrdotdiv      - elmentwise division of two real quaternion arrays

    qrdotmult     - elmentwise multiplication of two real quaternion arrays

    qrmult        - multiply two real quaternion arrays

    qrpermute     - permute the indices of a quaternion array

    rectifyhomog  - Apply rectifing homographies to a set of cameras to make their optical axes parallel

    rot--2--      - Convert between different representations of rotations

    rotqrmean     - Find the average of several rotation quaternions

    rotqrvec      - Apply a quaternion rotation to an array of 3D vectors

    sphrharm      - forward and inverse spherical harmonic transform using uniform, Gaussian

                    or arbitrary inclination (elevation) grids and a uniform azimuth grid.

    upolyhedron   - Calculate the vertex coordinates and other characteristics of a uniform polyhedron

 

  Printing and Display functions打印展示函数

    axisenlarge   - Selectively enlarge figure axis for clarity

    cblabel       - Add a label onto the colorbar

    figbolden     - Make a figure bold and adjust colours for printing clearly

    fig2emf       - Make a figure bold and save as a windows metafile

    frac2bin      - Convert numbers to fixed-point binary strings

    lambda2rgb    - convert wavelength to XYZ or RGB colour triplets

    sprintsi      - Print a value with an SI multiplier

    sprintcpx     - Print a complex number with real and imaginary parts

    texthvc       - write text on a plot with specified alignment and colour

    tilefigs      - Arrange all figures on the screen

    v_colormap    - Set and plot colormap information

    xticksi       - Label x-axis tick marks using SI multipliers

    yticksi       - Label y-axis tick marks using SI multipliers

    xyzticksi     - Helper function for xticksi and yticksi

 

  Voicebox Parameters and System Interface音频工具参数和系统接口

    voicebox      - Global installation-dependent parameters

    unixwhich     - Search the WINDOWS system path for an executable program (like UNIX which)

    winenvar      - Obtain WINDOWS environment variables

 

  Utility Functions功能函数

    atan2sc       - arctangent function that returns the sin and cos of the angle反正切函数，返回sin和cos的角度

    bitsprec      - Rounds values to a precision of n bits

    choosenk      - All choices of k elements out of 1:n without replacement

    choosrnk      - All choices of k elements out of 1:n with replacement

    dlyapsq       - Solve the discrete lyapunov equation

    dualdiag      - Simultaneously diagonalise two hermitian matrices

    finishat      - Estimate the finishing time of a long loop

    fopenmkd      - like FOPEN() but creates any missing directories/folders

    hostipinfo    - Get information about the computer name and internet connections

    hypergeom1f1  - Confluent Hypergeometric function or Kummer's M function

    logsum        - Calculates log(sum(exp(x))) without overflow/underflow

    minspane      - calculate the minimum (or shortest) spanning tree

    mintrace      - find a row permutation to minimize the trace of a matrix

    m2htmlpwd     - Create HTML documentation of matlab routines in the current directory

    nearnonz      - Replace each zero element with the nearest non-zero element

    permutes      - All n! permutations of 1:n

    quadpeak      - Find quadratically-interpolated peak in a 2D array

    rotation      - Generate rotation matrices

    skew3d        - Generate 3x3 skew symmetric matrices

    zerotrim      - Remove empty trailing rows and columns

 

 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

voicebox 既是目录也是函数。

 voicebox  set global parameters for Voicebox functions Y=(FIELD,VAL)

 

   Inputs:  F   is a field name

            V   is a new value for the field

 

  Outputs:  Y   is set equal to the structure of parameters if the

                f and v inputs are both present or both absent. If only

                input f is specified, then y is set to the value of the

                corresponding field or null if it doesn't exist.

 

  You can override the defaults set here by setting the environment variable "voicebox"

  to the path of an m-file that contains lines like "% PP.dir_temp='F:\TEMP';"

 

  This routine contains default values for constants that are used by

  other functions in the voicebox toolbox. Values in the first section below,

  entitled "System-dependent directory paths" should be set as follows:

 

     PP.dir_temp     directory for storing temporary files

     PP.dir_data     default directory to preappend to speech data file names

                     when the "d" option is specified in READWAV etc.

     PP.shorten      location of SHORTEN executable. SHORTEN is a proprietary file compression

                     algorithm that is used for some SPHERE-format files. READSPH

                     will try to call an external decoder if it is asked to

                     read such a compressed file.

     PP.sfsbin       location of Speech Filing Sysytem binaries. If the "c" option

                     is given to READSFS, it will try to create a requested item

                     if it is not present in the SFS file. This parameter tells it

                     where to find the SFS executables.

     PP.sfssuffix    suffix for Speech Filing Sysytem binaries. READSFS uses this paremeter

                     to create the name of an SFS executable (see PP.sfsbin above).

  Other values defined in this routine are the defaults for specific algorithm constants.

  If you want to change these, please refer to the individual routines for a fuller description.

原文，使用help dirname

可以查看

因为我把那些.m文件放在voicebox里面，所以使用help voicebox 有如下

Voicebox: Speech Processing Toolbox for MATLAB
Some files have been prefixed "v_" to avoid name conflicts

Audio File Input/Output
readwav - Read a WAV file
writewav - Write a WAV file
readhtk - Read HTK waveform files
writehtk - Write HTK waveform files
readsfs - Read SFS files
readsph - Read SPHERE/TIMIT waveform files
readaif - Read AIFF Audio Interchange file format file
readcnx - Raed BT Connex database files
readau - Read AU files (from SUN)
readflac - Read FLAC files

Frequency Scales
frq2bark - Convert Hz to the Bark frequency scale
frq2cent - Convert Hertz to cents scale
frq2erb - Convert Hertz to erb rate scale
frq2mel - Convert Hertz to mel scale
frq2midi - Convert Hertz to midi scale of semitones
bark2frq - Convert the Bark frequency scale to Hz
cent2frq - Convert cents scale to Hertz
erb2frq - Convert erb rate scale to Hertz
mel2frq - Convert mel scale to Hertz
midi2frq - Convert midi scale of semitones to Hertz

Fourier/DCT/Hartley Transforms
rfft - FFT of real data
irfft - Inverse of FFT of real data
rsfft - FFT of real symmetric data
rdct - DCT of real data
irdct - Inverse of DCT of real data
rhartley - Hartley transform of real data
zoomfft - calculate the fft over a portion of the spectrum with any resolution
sphrharm - calculate forward and inverse shperical harmonic transformations

Probability Distributions
berk2prob - Convert Berksons to probability
gaussmix - Fit a gaussian mixture model to data values
gaussmixd - Calculate marginal and conditional density distributions and perform inference
gaussmixk - Estimate Kuleck-Leibler divergence between two GMMs
gaussmixg - Calculate global mean, covariance and mode of a Gaussian mixture
gaussmixm - Estimate mean and variance of GMM vector magnitude
gaussmixp - Calculates and plots full and marginal probability density from a GMM
gaussmixt - multiplies two GMMs together
gausprod - Calculate the product of multiple gaussians
gmmlpdf - OBSOLETE - use gaussmixp instead
histndim - N-dimensional histogram (+ plot 2-D histogram)
lognmpdf - Prob density function of a lognormal distribution
maxgauss - Calculate the mean and variance of max(x) where x is a gaussian vector
normcdflog - Calculate the log of the Normal cdf without underflow
prob2berk - Convert probability to Berksons
randvec - Generate random vectors
randiscr - Generate discrete random values with prescribed probabilities
rnsubset - Select a random subset
randfilt - Generate filtered random noise without transients
stdspectrum - Generate standard audio and speech spectra
usasi - Generate USASI noise (obsolete: use stdspectrum instead)
v_chimv - Approximate mean and variance of non-central chi distribution
vonmisespdf - Calculate the pdf of the Von Mises (circular normal) distribution

Vector Distances
disteusq - Calculate euclidean/mahanalobis distances between two sets of vectors
distchar - COSH spectral distance between AR coefficient sets
distitar - Itakura spectral distance between AR coefficient sets
distisar - Itakura-Saito spectral distance between AR coefficient sets
distchpf - COSH spectral distance between power spectra
distitpf - Itakura spectral distance between power spectra
distispf - Itakura-Saito spectral distance between power spectra

Speech Analysis
activlev - Calculate the active level of speech (ITU-T P.56)
activlevg - Calculate the active level of speech robustly to added noise
dypsa - Estimate glottal closure instants from a speech waveform
enframe - Divide a speech signal into frames for frame-based processing
correlogram - calculate a 3-D correlogram
ewgrpdel - Energy-weighted group delay waveform
fram2wav - Interpolate frame-based values to a waveform
filtbankm - Transformation matrix for a linear/mel/erb/bark-spaced filterbank from dft output
fxpefac - PEFAC pitch tracker
fxrapt - RAPT pitch tracker
gammabank - Calculate a bank of IIR gammatone filters
importsii - Calculate the SII importance function (ANSI S3.5-1997)
modspect - Caluclate the modulation specrogram
mos2pesq - Convert MOS values to equivalent PESQ scores
overlapadd - Reconstitute an output waveform after frame-based processing
pesq2mos - Convert PESQ scores to equivalent MOS values
phon2sone - Convert signal levels from phons to sones
psycdigit - Experimental estimation of monotonic/unimodal psychometric function using TIDIGITS
psycest - Experimental estimation of monotonic psychometric function
psycestu - Experimental estimation of unimodal psychometric function
psychofunc - Psychometric functions
v_sigma - Identify glottal closure and opening intstants from Lx or EGG waveform
snrseg - Segmental SNR and Global SNR calculation
sone2phon - Convert signal levels from sones to phons
soundspeed - Returns the speed of sound in air as a function of temperature
spgrambw - Spectrogram with many options
stoi2prob - Convert STOI intelligibility measure to probability of correct recognition
txalign - Align two sets of time markers
vadsohn - Voice activity detector
v_ppmvu - Calculate the PPM, VU or EBU levels of a signal

LPC Analysis of Speech
ccwarpf - warp complex cepstrum coefficients
lpcauto - LPC analysis: autocorrelation method
lpcbwexp - Bandwidth expansion of LPC filter
lpccovar - LPC analysis: covariance method
lpcconv - Arbitrary conversion between LPC representations
lpcifilt - inverse filter a speech signal
lpcrand - create random stable filters
lpcrr2am - Matrix with all LPC filters up to order p
lpcstable - check for stability and force stable filters
lpc--2-- - Convert between alternative LPC representation

Speech Synthesis
sapisynth - Text-to-speech synthesis of a string or matrix
glotros - Rosenberg model of glottal waveform
glotlf - Liljencrants-Fant model of glottal waveform

Speech Enhancement
estnoiseg - Estimate the noise spectrum from noisy speech using MMSE method
estnoisem - Estimate the noise spectrum from noisy speech using minimum statistics
specsub - Speech enhancement using spectral subtraction
ssubmmse - Speech enhancement using MMSE estimate of spectral amplitude or log amplitude
ssubmmsev - Speech enhancement using MMSE estimate and VAD-based noise estimation
specsubm - (obsolete algorithm) Spectral subtraction
spendred - Speech Enhancement and Dereverberation (Doire's algorithm)

Speech Coding
lin2pcmu - Convert linear PCM to mu-law PCM
pcma2lin - Convert A-law PCM to linear PCM
pcmu2lin - Convert mu-law PCM to linear PCM
lin2pcma - Convert linear PCM to A-law PCM
kmeanlbg - Vector quantisation: LBG algorithm
kmeanhar - Vector quantization: K-harmonic means
potsband - Create telephone bandwidth filter
v_kmeans - Vector quantisation: k-means algorithm

Speech Recognition
melbankm - Mel filterbank transformation matrix
melcepst - Mel cepstrum frontend for recogniser
cep2pow - Convert mel cepstram means & variances to power domain
pow2cep - Convert power domain means & variances to mel cepstrum
ldatrace - constrained Linear Discriminant Analysis to maximize trace(W\B)

Signal Processing
ditherq - Add dither and quantize a signal
filterbank - Apply a bank of IIR filters to a signal
maxfilt - Running maximum filter
meansqtf - Output power of a filter with white noise input
momfilt - Generate running moments
schmitt - Pass a signal through a schmitt trigger
sigalign - Align a clean refeence with a noisy signal
teager - Calculate the Teager energy waveform
v_addnoise - Add noise to a signal at a chosen SNR
v_findpeaks - Find peaks in a signal or spectrum
v_resample - Resamples a signal: identical to MATLAB resample but removes filter transients
v_windinfo - Calculate window properties and figures of merit
v_windows - Window function generation
zerocros - Find interpolated zero crossings

Information Theory
huffman - Generate Huffman code
entropy - Calculate entropy and conditional entropy

Computer Vision
imagehomog - Apply a homography transformation to an image with bilinear interpolation
polygonarea - Calculate the area of a polygon
polygonwind - Test if points are inside or outside a polygon
polygonxline - Find where a line crosses a polygon
qrabs - Absolute value of a real quaternion
qrdivide - divide two real quaternions (or invert one)
qrdotdiv - elmentwise division of two real quaternion arrays
qrdotmult - elmentwise multiplication of two real quaternion arrays
qrmult - multiply two real quaternion arrays
qrpermute - permute the indices of a quaternion array
rectifyhomog - Apply rectifing homographies to a set of cameras to make their optical axes parallel
rot--2-- - Convert between different representations of rotations
rotqrmean - Find the average of several rotation quaternions
rotqrvec - Apply a quaternion rotation to an array of 3D vectors
sphrharm - forward and inverse spherical harmonic transform using uniform, Gaussian
or arbitrary inclination (elevation) grids and a uniform azimuth grid.
upolyhedron - Calculate the vertex coordinates and other characteristics of a uniform polyhedron

Printing and Display functions
axisenlarge - Selectively enlarge figure axis for clarity
cblabel - Add a label onto the colorbar
figbolden - Make a figure bold and adjust colours for printing clearly
fig2emf - Make a figure bold and save as a windows metafile
frac2bin - Convert numbers to fixed-point binary strings
lambda2rgb - convert wavelength to XYZ or RGB colour triplets
sprintsi - Print a value with an SI multiplier
sprintcpx - Print a complex number with real and imaginary parts
texthvc - write text on a plot with specified alignment and colour
tilefigs - Arrange all figures on the screen
v_colormap - Set and plot colormap information
xticksi - Label x-axis tick marks using SI multipliers
yticksi - Label y-axis tick marks using SI multipliers
xyzticksi - Helper function for xticksi and yticksi

Voicebox Parameters and System Interface
voicebox - Global installation-dependent parameters
unixwhich - Search the WINDOWS system path for an executable program (like UNIX which)
winenvar - Obtain WINDOWS environment variables

Utility Functions
atan2sc - arctangent function that returns the sin and cos of the angle
bitsprec - Rounds values to a precision of n bits
choosenk - All choices of k elements out of 1:n without replacement
choosrnk - All choices of k elements out of 1:n with replacement
dlyapsq - Solve the discrete lyapunov equation
dualdiag - Simultaneously diagonalise two hermitian matrices
finishat - Estimate the finishing time of a long loop
fopenmkd - like FOPEN() but creates any missing directories/folders
hostipinfo - Get information about the computer name and internet connections
hypergeom1f1 - Confluent Hypergeometric function or Kummer's M function
logsum - Calculates log(sum(exp(x))) without overflow/underflow
minspane - calculate the minimum (or shortest) spanning tree
mintrace - find a row permutation to minimize the trace of a matrix
m2htmlpwd - Create HTML documentation of matlab routines in the current directory
nearnonz - Replace each zero element with the nearest non-zero element
permutes - All n! permutations of 1:n
quadpeak - Find quadratically-interpolated peak in a 2D array
rotation - Generate rotation matrices
skew3d - Generate 3x3 skew symmetric matrices
zerotrim - Remove empty trailing rows and columns

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

voicebox 既是目录也是函数。

voicebox set global parameters for Voicebox functions Y=(FIELD,VAL)

Inputs: F is a field name
V is a new value for the field

Outputs: Y is set equal to the structure of parameters if the
f and v inputs are both present or both absent. If only
input f is specified, then y is set to the value of the
corresponding field or null if it doesn't exist.

You can override the defaults set here by setting the environment variable "voicebox"
to the path of an m-file that contains lines like "% PP.dir_temp='F:\TEMP';"

This routine contains default values for constants that are used by
other functions in the voicebox toolbox. Values in the first section below,
entitled "System-dependent directory paths" should be set as follows:

PP.dir_temp directory for storing temporary files
PP.dir_data default directory to preappend to speech data file names
when the "d" option is specified in READWAV etc.
PP.shorten location of SHORTEN executable. SHORTEN is a proprietary file compression
algorithm that is used for some SPHERE-format files. READSPH
will try to call an external decoder if it is asked to
read such a compressed file.
PP.sfsbin location of Speech Filing Sysytem binaries. If the "c" option
is given to READSFS, it will try to create a requested item
if it is not present in the SFS file. This parameter tells it
where to find the SFS executables.
PP.sfssuffix suffix for Speech Filing Sysytem binaries. READSFS uses this paremeter
to create the name of an SFS executable (see PP.sfsbin above).
Other values defined in this routine are the defaults for specific algorithm constants.
If you want to change these, please refer to the individual routines for a fuller description.