VOICEBOX: Speech Processing Toolbox for MATLAB
Introduction
VOICEBOX is a speech processing toolbox consists of MATLAB routines that are
maintained by and mostly written by
, , Exhibition
Road, London SW7 2BT, UK. Several of the routines require MATLAB V6.5 or above
and require (normally slight) modification to work with earlier veresions.
The routines are available as a&
and are made available under the terms of the .
The routine
various installation-dependent parameters which may need to be altered before
using the toolbox. In particular it contains a number of default directory paths
indicating where temporary files should be created, where speech data normally
resides, etc. You can override these defaults by editing voicebox.m directly or,
more conveniently, by setting an environment variable VOICEBOX to the path of an
initializing m-file. See the comments in
for a fuller description.
For reading compressed SPHERE format files, you will need the
program written by Tony Robinson and SoftSound
Limited . The path to
the shorten executable must be set in .Unfortunately, the current version does not work on 64-bit
MATLAB doesn't reall some non-unicode fonts containing
IPA phonetic symbols developed by
available .
Please send any comments, suggestions, bug reports etc to
Read and write WAV and other speech file formats
Convert between Hz, Mel, Erb and MIDI frequency scales
Various related transforms
Generate random vectors and noise signals
Calculate distances between vector lists
Active level estimation, Spectrograms
Linear Predictive Coding routines
Text-to-speech synthesis and glottal waveform models
Spectral noise subtraction
PCM coding, Vector quantisation
Front-end processing for recognition
Miscellaneous signal processing functions
Routines for entropy calculation and symbol codes
Routines for 3D rotation
Utilities for printing and graphics
Get or set VOICEBOX and WINDOWS system parameters
Miscellaneous utility functions
Routines are available to read and, in some cases write, a variety of
file formats:
These routines allow an arbitrary number of channels and can
deal with linear PCM (any precision up to 32 bits), A-law PCM,
Mu-law PCM and Floating point formats. Large files can be read and
written in small chunks.
Read and write waveform and parameter files used by Microsoft's
Hidden Markov Toolkit.
Speech Filing system files from Mark Huckvale at UCL.
NIST Sphere format files (including TIMIT). Needs
for compressed files.
AIFF format (Audio Interchange File Format) used by Mac users.
Read Connex database files (from BT)
Read AV audio files (from Sun)
The bark scale is based on critical bands and masking in
the human ear.
The cent scale is in increments of 0.01 semitones.
The erb scale is based on the equivalent rectangular
bandwidths of the human ear.
The mel scale is based on the human perception of
sinewave pitch.
The midi standard specifies a numbering of semitones
with middle C being 60. They can use the normal equal tempered scale
or else the pythagorean scale of just intonation. They will in
addition output note names in a character format.
Forward and inverse discrete fourier transforms on real data.
Only the first half of the conjugate symmetric transform is
generated. For even length data, the inverse routine is
asumptotically twice as fast as the built-in MATLAB routine.
Forward transform of real, symmetric data to give the first half
only of the real, symmetric transform.
Calculate the discrete fourier transform at an arbitrary set of
linearly spaced frequencies. Can be used to zoom into a subset of
the full frequency range.
Forward and inverse discrete cosine transform on real data.
Hartley transform on real data (forward and inverse transforms
are the same).
Random Number Generation
generates random vectors from gaussian
or lognormal mixture distributions.
generates discrete random values with a specified
probability vector
generates noise samples or filter coefficients for a
variety of standard spectra including: A, B, C or BS468 weighting,
USASI noise, POTS spectrum, LTASS, Internal masking noise (from SII
generates filtered gaussian noise without any
startup transients.
selects a random subset of k elements from
the numbers 1:n
Probability Density Functions
calculates the pdf of a lognormal distribution
generates a multivariate Gaussian mixture model (GMM) from
training data
determines marginal and conditional distributions from a GMM and
can be used to perform inference on unobserved variables.
calculates the global mean, covariance matrix and mode of a GMM
estimates the mean and variance of the magnitude of a GMM vector
calculates the Kulback-Leibler Divergence, D(f||g), between two
calculates and plots full and marginal log probability and
relative mixture probabilities from a GMM
multiplies two GMMs together
approximates the mean and variance of a non-central chi
distribution
calculate the pdf of the Von Mises (circular normal)
distribution
Miscellaneous
convert Berkson matrix to probability
calculates the product of two gaussian distributions
calculates an n-dimensional histogram (and plots a
calculates the mean and variance of the maximum element of a
gaussian vector
convert probability matrix to Berksons
calculates the squared euclidean distance between
all pairs of rows of two matrices.
calculates the Itakura spectral distances between sets of AR
coefficients.
calculates the Itakura spectral distances between power spectra.
calculates the Itakura-Saito spectral distances between sets of
AR coefficients.
calculates the Itakura-Saito spectral distances between power
calculates the COSH spectral distances between sets of AR
coefficients.
calculates the COSH spectral distances between power spectra.
calculates the active level of a speech segment according to
ITU-T recommendation P.56.
calculates the active level of a speech segment robustly to
added noise
estimates the glottal closure instants from the speech waveform.
can be used to split a signal up into frames. It can
optionally apply a window to each frame.
Calculates a 3D correlogram [slowly]
calculates the energy-weighted group delay waveform.
interpolates a sequence of frame-based value into a waveform
Transformation matrix for a linear/mel/erb/bark-spaced
filterbank from dft output
PEFAC pitch tracker
is an implementation of the RAPT pitch tracker by David Talkin.
Determine a bank of IIR gammatone filters
calculate the SII importance function
Convert MOS values to PESQ speech quality scores
Join frames up using overlap-add processing. Commonly used with
Convert PESQ speech quality scores to MOS values
Convert signal levels from phons to sones
experimental estimation of monotonic/unimodal psychometric
function using TIDIGITS
experimental estimation of monotonic psychometric function
experimental estimation of unimodal psychometric function
calculate psychometric function
estimate glottal opening and closure instants from the
laryngograph/EGG waveform
calculate segmental SNR and global SNR relative to a reference
Convert signal levels from sones to phons
gives the speed of sound as a function of temperature
draws a spectrogram with many options. See
finds the best alignment (in a least squares sense) between two
sets of time markers (e.g. glottal closure instants).
voice activity detector
Calculate the PPM, VU or EBU levels of a signal
perform linear predictive coding (LPC) analysis. The
routines relating to LPC are described in more detail on
. A large number of
are included for changing
the form of the LPC coefficients (e.g. AR coefficients, reflection
coefficients etc.): these are of the form lpcxx2yy where xx and yy
denote the coefficient sets.
calculates LPC filters for all orders up to a given maximum.
performs bandwidth expansion on an LPC filter.
performs frequency warping in the complex cepstrum domain.
performs inverse filtering to estimate the glottal waveform from
the speech signal and the lpc coefficients.
can be used to generate random, stable filters for testing
Text-to-speech synthesis (TTS) of a string or matrix
Calculates the Rosenberg model of the glottal flow
Calculates the Liljencrants-Fant model of the glottal flow
uses an MMSE algorithm to estimate the noise
spectrum from a noisy speech signal that has been divided into
uses a minimum-statistics algorithm to estimate the
noise spectrum from a noisy speech signal that has been divided into
performs speech enhancement using spectral subtraction
performs speech enhancement using the MMSE or log MMSE criteria
performs speech enhancement using the MMSE or log MMSE criteria
with VAD-based noise estimate
converts an audio waveform to 8-bit A-law PCM format
converts an audio waveform to 8-bit mu-law PCM format
converts 8-bit A-law PCM to a waveform
converts 8-bit mu-law PCM to a waveform
vector quantisation using the LBG algorithm
vector quantisation using the K-harmonic means algorithm
calculates a bandpass filter corresponding to the standard
telephone passband.
vector quantisation using the K-means algorithm
implements a mel-cepstrum front end for a recogniser
constructs a bandpass filterbank with mel-spaced centre
frequencies
converts multivariate Gaussian means and covariances from the
log power or cepstral domain to the power domain
converts multivariate Gaussian means and covariances from the
power domain to the log power or cepstral domain
performs Linear Discriminant Analysis with optional constraints
on the transform matrix
Signal Processing
adds dither and quantizes a signal
solves the discrete lyapunov equation using an efficient square
root algorithm
Apply a bank of IIR filters to a signal
performs running maximum filter
calculates the output power of a rational filter with a white
noise input
generate running moments from a signal
align a clean reference with a noise signal and find optimum
passes a signal through a schmitt trigger having hysteresis
calculate the Teager energy waveform
add noise to a signal at a chosen SNR
finds the peaks in a signal
generates window functions
calculate window properties and figures of merit
finds the zero crossings of a signal with interpolation
calculates optimum D-ary symbol code from a
probability mass vector
calculates entropy and conditional entropy for discrete and
continuous distributions
Apply a homography transformation to an image with
bilinear interpolation
Calculates the area of a polygon
Determines whether points are inside or outside a
Determines where a line crosses a polygon
Absolute value of a real quaternion
divide two real quaternions (or invert one)
elmentwise division of two real quaternion arrays
elmentwise multiplication of two real quaternion
multiply two real quaternion arrays
permute the indices of a quaternion array
Apply rectifing homographies to a set of cameras to
make their optical axes parallel
converts between the following representations of
rotations: rotation matrix (ro), euler angles (eu), axis of rotation
(ax), plane of rotation (pl), real quaternion vector (qr), real
quaternion matrix (mr), complex quaternion vector (qc), complex
quaternion matrix (mc). A detailed description is given
Find the average of several rotation quaternions
Apply a quaternion rotation to an array of 3D
Convert between vectors and skew symmetric matrices:
3x3 matrix &-& 3x1 vector and 4x4 Plucker matrix &-& 6x1 vector.
forward and inverse spherical harmonic transform
using uniform, Gaussian or arbitrary inclination (elevation) grids
and a uniform azimuth grid.
Calculate the vertex coordinates and other
characteristics of a uniform polyhedron
enlarge the axes of a figure slightly
rounds values to a precision of n bits
add a label to the colourbar
makes the lines on a figure bold, enlarges font
sizes and adjusts colours for printing clearly
optionally makes the lines on a figure bold and then
saves in windows metafile format
converts numbers to fixed-point binary strings
convert wavelength to an RGB or XYZ triplet
prints a value with the correct standard SI multiplier (e.g.
2100 prints as 2.1 k)
add text to plots with specified alignment and colour
arrange all figures on the screen
set and display colormap information including colormaps that
print well in monochrome
Label the x-axis tick marks using SI multipliers for large and
small values. Particularly useful for logarithmic plots.
Label the y-axis tick marks using SI multipliers for large and
small values. Particularly useful for logarithmic plots.
contains a number of installation-dependent global
parameters and is likely to need editing for each particular setup.
searches the WINDOWS system path for an executable (like UNIX
which command)
Obtains WINDOWS environment variables
arctangent function that returns the sin and cos of
Rounds values to a precision of n bits
all possible ways of choosing k elements out of the
numbers 1:n without duplications
all possible ways of choosing k elements out of the
numbers 1:n with duplications allowed
Solve the discrete lyapunov equation
simultaneously diagonalises two matrices: this is
useful in computing LDA or IMELDA transforms.
Estimate the finishing time of a long loop
Equivalent to FOPEN() but creates any
missing directories/folders
Gives information about computer name and internet
connections
calculates log(sum(exp(x))) without overflow
Calculates the minimum spanning tree (a.k.a.
shortest spanning tree) of a set of n-dimensional points
Find a row permutation to minimize the trace of a
Create HTML documentation of matlab routines in the
current directory
Replace zero elements by the nearest non-zero
all possible permutations of the numbers 1:n
find a quadratically-interpolated peak in a
N-dimensional array by fitting a quadratic function to the array
generates rotation matrices
removes from a matrix any trailing rows
and columns that are all zero.修理的喜欢 | LOFTER（乐乎） - 每个人的理想国
LOFTER for ipad —— 记录生活，发现同好
修理 的喜欢
{list photos as photo}
{if photo_index==0}{break}{/if}
品牌${make||'-'}
型号${model||'-'}
焦距${focalLength||'-'}
光圈${apertureValue||'-'}
快门速度${exposureTime||'-'}
ISO${isoSpeedRatings||'-'}
曝光补偿${exposureBiasValue||'-'}
镜头${lens||'-'}
{if defined('posts')&&posts.length>0}
{list posts as post}
{if post_index < 3}
{if post.type == 1 || post.type == 5}
{if !!post.title}${post.title|escape}{/if}
{if !!post.digest}${post.digest}{/if}
{if post.type == 2}
{if post.type == 3}
{if post.type == 4}
{if data.msgRank == 1}{/if}
{if data.askSetting == 1}{/if}
{if defined('posts')&&posts.length>0}
{list posts as post}
{if post.type == 2}
{if post.type == 3}
{if post.type == 4}
this.p={ dwrMethod:'queryLikePosts',fpost:'',userId:2260474,blogListLength:30};Matlab Edge Detection Example
% This demo is known to work with:
Matlab Version 7.10.0.499 (R2010a)
Image Processing Toolbox Version 7.0 (R2010a)
A = imread('wheel.png');
% Marr/Hildreth edge detection
% with threshold forced to zero
MH1 = edge(A,'log',0,1.0);
MH2 = edge(A,'log',0,2.0);
MH3 = edge(A,'log',0,3.0);
MH4 = edge(A,'log',0,4.0);
% form mosaic
EFGH = [ MH1 MH2; MH3 MH4];
%% show mosaic in Matlab Figure window
log = figure('Name','Marr/Hildreth: UL: s=1
BL: s=3 BR: s=4');
iptsetpref('ImshowBorder','tight');
imshow(EFGH,'InitialMagnification',100);
% Canny edge detection
[C1, Ct1] = edge(A,'canny',[],1.0);
[C2, Ct2] = edge(A,'canny',[],2.0);
[C3, Ct3] = edge(A,'canny',[],3.0);
[C4, Ct4] = edge(A,'canny',[],4.0);
% Recompute lowering both automatically computed
% thresholds by fraction k
C1 = edge(A,'canny',k*Ct1,1.0);
C2 = edge(A,'canny',k*Ct2,2.0);
C3 = edge(A,'canny',k*Ct3,3.0);
C4 = edge(A,'canny',k*Ct4,4.0);
% form mosaic
ABCD = [ C1 C2; C3 C4 ];
% show mosaic in Matlab Figure window
canny = figure('Name','Canny: UL: s=1
BL: s=3 BR: s=4');
iptsetpref('ImshowBorder','tight');
imshow(ABCD,'InitialMagnification',100);
% uncomment to write results to file
%imwrite(ABCD,'canny.pbm','pbm');
%imwrite(EFGH,'log.pbm','pbm');
CPSC 505 course material (this page last updated October 3, 2013) 上传我的文档
 下载
 收藏
该文档贡献者很忙，什么也没留下。
 下载此文档
正在努力加载中...
基子MAATLAB的采空区自燃发火的数值模拟分析
下载积分：999
内容提示：基子MAATLAB的采空区自燃发火的数值模拟分析
文档格式：PDF|
浏览次数：0|
上传日期： 07:58:08|
文档星级：
该用户还上传了这些文档
基子MAATLAB的采空区自燃发火的数值模拟分析
官方公共微信
