matlab⼯具voicebox函数中⽂说明
matlab⼯具voicebox函数中⽂说明
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
宾主尽东南之美readaif - 读 AIFF Audio Interchange file format ⽂件
readcnx - 读 BT Connex databa 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 mitones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
太平公主之死
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 mitones 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 - Inver 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 - Inver 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 inver 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
古原草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 - u 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
rnsubt - Select a random subt选择的⼀个随机⼦集
randfilt - Generate filtered random noi 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 noi (obsolete: u 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
vonmispdf - Calculate the pdf of the Von Mis (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 ts 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 ts AR系数集之间的双曲余弦谱距离
distitar - Itakura spectral distance between AR coefficient ts AR系数集之间的Itakura谱距离
distisar - Itakura-Saito spectral distance between AR coefficient ts 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 noi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-bad 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-bad values to a waveform波形中插⼊帧值
好词好句子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-bad 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
snrg - 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 ts 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 reprentations LPC表⽰的任意转换
lpcifilt - inver 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 reprentation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 - Ronberg 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
estnoig - Estimate the noi 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
estnoim - Estimate the noi 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
ssubmm - 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
ssubmmv - Speech enhancement using MMSE estimate and VAD-bad noi 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 recognir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
好词佳句摘抄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 noi input带有⽩噪声输⼊的波滤器的的功率输出
检验员资格证
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_addnoi - Add noi to a signal at a chon 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 zerocro
s(y,'n') 默认全部或者'b'）野猪肉可以吃吗
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 cross a polygon
qrabs - Absolute value of a real quaternion
qrdivide - divide two real quaternions (or invert one)
qrdotdiv - elmentwi division of two real quaternion arrays
qrdotmult - elmentwi multiplication of two real quaternion arrays
qrmult - multiply two real quaternion arrays
qrpermute - permute the indices of a quaternion array壮字开头的成语
rectifyhomog - Apply rectifing homographies to a t of cameras to make their optical axes parallel
rot--2-- - Convert between different reprentations of rotations
rotqrmean - Find the average of veral rotation quaternions
rotqrvec - Apply a quaternion rotation to an array of 3D vectors
sphrharm - forward and inver 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
