ocvolume.dsp
Class featureExtraction

java.lang.Object
  |
  +--ocvolume.dsp.featureExtraction

public class featureExtraction

extends java.lang.Object

last updated on June 15, 2002
description: feature extraction class used to extract mel-frequency cepstral coefficients from input signal
calls: none
called by: volume, train
input: speech signal
output: mel-frequency cepstral coefficient

Field Summary

protected static fft	FFT Fast Fourier Transformation
protected static int	fftSize FFT Size (Must be be a power of 2)
protected static int	frameLength Number of samples per frame
protected static double[][]	frames All the frames of the input signal
protected static double[]	hammingWindow hamming window values
protected static double	lowerFilterFreq lower limit of filter (or 64 Hz?)
protected static int	numCepstra Number of MFCCs per frame
protected static int	numMelFilters number of mel filters (SPHINX-III uses 40)
protected static double	preEmphasisAlpha Pre-Emphasis Alpha (Set to 0 if no pre-emphasis should be performed)
protected static double	samplingRate sample rate in Hz
protected static int	shiftInterval Number of overlapping samples (usually 50% of frame length)
protected static double	upperFilterFreq upper limit of filter (or half of sampling freq.?)

Constructor Summary

featureExtraction()

Method Summary

protected static void	framing(double[] inputSignal) performs Frame Blocking to break down a speech signal into frames calls: none called by: featureExtraction
protected static double	freqToMel(double freq) convert frequency to mel-frequency calls: none called by: featureExtraction
protected static double	log10(double value) calculates logarithm with base 10 calls: none called by: featureExtraction
protected static double[]	magnitudeSpectrum(double[] frame) computes the magnitude spectrum of the input frame calls: none called by: featureExtraction
protected static double[]	preEmphasis(short[] inputSignal) perform pre-emphasis to equalize amplitude of high and low frequency calls: none called by: featureExtraction
static double[][]	process(short[] inputSignal) takes a speech signal and returns the Mel-Frequency Cepstral Coefficient (MFCC) calls: fft called by: volume, train

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

samplingRate

protected static final double samplingRate

sample rate in Hz

See Also:

Constant Field Values

frameLength

protected static final int frameLength

Number of samples per frame

See Also:

Constant Field Values

shiftInterval

protected static final int shiftInterval

Number of overlapping samples (usually 50% of frame length)

See Also:

Constant Field Values

numCepstra

protected static final int numCepstra

Number of MFCCs per frame

See Also:

Constant Field Values

fftSize

protected static final int fftSize

FFT Size (Must be be a power of 2)

See Also:

Constant Field Values

preEmphasisAlpha

protected static final double preEmphasisAlpha

Pre-Emphasis Alpha (Set to 0 if no pre-emphasis should be performed)

See Also:

Constant Field Values

lowerFilterFreq

protected static final double lowerFilterFreq

lower limit of filter (or 64 Hz?)

See Also:

Constant Field Values

upperFilterFreq

protected static final double upperFilterFreq

upper limit of filter (or half of sampling freq.?)

See Also:

Constant Field Values

numMelFilters

protected static final int numMelFilters

number of mel filters (SPHINX-III uses 40)

See Also:

Constant Field Values

frames

protected static double[][] frames

All the frames of the input signal

hammingWindow

protected static double[] hammingWindow

hamming window values

FFT

protected static fft FFT

Fast Fourier Transformation

Constructor Detail

featureExtraction

public featureExtraction()

Method Detail

process

public static double[][] process(short[] inputSignal)

takes a speech signal and returns the Mel-Frequency Cepstral Coefficient (MFCC)
calls: fft
called by: volume, train

Parameters:

inputSignal - Speech Waveform (16 bit integer data)

Returns:

Mel Frequency Cepstral Coefficients (32 bit floating point data)

log10

protected static double log10(double value)

calculates logarithm with base 10
calls: none
called by: featureExtraction

Parameters:

value - Number to take the log of

Returns:

base 10 logarithm of the input values

freqToMel

protected static double freqToMel(double freq)

convert frequency to mel-frequency
calls: none
called by: featureExtraction

Parameters:

freq - Frequency

Returns:

Mel-Frequency

magnitudeSpectrum

protected static double[] magnitudeSpectrum(double[] frame)

computes the magnitude spectrum of the input frame
calls: none
called by: featureExtraction

Parameters:

frame - Input frame signal

Returns:

Magnitude Spectrum array

framing

protected static void framing(double[] inputSignal)

performs Frame Blocking to break down a speech signal into frames
calls: none
called by: featureExtraction

Parameters:

inputSignal - Speech Signal (16 bit integer data)

preEmphasis

protected static double[] preEmphasis(short[] inputSignal)

perform pre-emphasis to equalize amplitude of high and low frequency
calls: none
called by: featureExtraction

Parameters:

inputSignal - Speech Signal (16 bit integer data)

Returns:

Speech signal after pre-emphasis (16 bit integer data)