Welcome to the world of Scilab Speech

function list--Frequency analysis

1．lp_covariance

2．lp_covariance_m

3．lp_burg

4．lp_rmle

5．lp_plp

6．spec_fft

7．spec_perio

1．lp_covariance

　　----linear prediction spectral analysis by using convariance method.

Calling Sequence:

　　lp_covariance(wavefile);

　　lp_covariance(wavefile, window_type);

Parameters:

　　wavefile: wave file. Vector or matrix.

　　window_type: desired window type. Interger.

Description:

The covariance method estimates the LP parameters by minimizing an estimate of the prediction error power as well.

Examples:

x=wavread('d:\test.wav');

y=lp_covariance(x);

y=lp_covariance(x, 4);

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　back to top

2．lp_covariance_m

　　----linear prediction spectral analysis by using modified convariance method.

Calling Sequence:

　　lp_covariance_m(wavefile);

　　lp_covariance_m(wavefile, window_type);

Parameters:

　　wavefile: wave file. Vector or matrix.

　　window_type: desired window type. Interger.

Description:

The modified covariance method estimates the LP parameters by minimizing the average of the estimated forward and backward prediction error powers.

Examples:

x=wavread('d:\test.wav');

y=lp_covariance_m(x);

y=lp_covariance_m(x, 4);

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　back to top

3．lp_burg

　　----linear prediction spectral analysis by using burg algorithm.

Calling Sequence:

　　lp_burg(wavefile);

　　lp_burg(wavefile, window_type);

Parameters:

　　wavefile: wave file. Vector or matrix.

　　window_type: desired window type. Interger.

Description:

In contrast to the above methods, which estimate the LP parameters directly, the Burg method estimates the reflection coefficients first, and uses the Levinson recursion to obtain the LP parameter estimate. The reflection coefficient estimates are obtained by minimizing estimates of the prediction error power for different order predictors in a recursive manner.

Examples:

x=wavread('d:\test.wav');

y=lp_burg(x);

y=lp_burg(x, 4);

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　back to top

4．lp_rmle

　　----linear prediction spectral analysis by using recursive maximum likelihood algorithm.

Calling Sequence:

　　lp_rmle(wavefile);

　　lp_rmle(wavefile, window_type);

Parameters:

　　wavefile: wave file. Vector or matrix.

　　window_type: desired window type. Interger.

Description:

The recursive maximum likelihood algorithm operates in a recursive model order fashion, which allows one to successively fit higher order models to the data.

Examples:

x=wavread('d:\test.wav');

y=lp_rmle(x);

y=lp_rmle(x, 4);

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　back to top

5．lp_plp

　　----linear prediction spectral analysis by using perceptual linear prediction method.

Calling Sequence:

　　lp_plp(wavefile);

　　lp_plp(wavefile, window_type);

Parameters:

　　wavefile: wave file. Vector or matrix.

　　window_type: desired window type. Interger.

Description:

The perceptual linear prediction(PLP) analysis technique is based on well established psychophysical concepts of hearing. The speech signal is filtered by a critical band filter bank followed by an equal loudness pre-emphasis, and an intensity to loudness adjustment using the intensity-loudness power law. The auditory spectrum is then modeled by and LP model. The PLP analysis yields an auditory spectrum with relatively low-frequency resolution. Futhermore, the frequency resolution of the auditory spectrum is nonuniform. In the higher frequency range it has less resolution, which agrees with the characteristics of the human auditory system. The PLP method is more consistent with human hearing than the conventional LP method. The PLP method is computationally efficient and yields a low dimensional representation of speech.

Examples:

x=wavread('d:\test.wav');

y=lp_plp(x);

y=lp_plp(x, 4);

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　back to top

6．spec_fft

　　----estimating the power spectrum by using standard fast Fourier transform (FFT) techniques.

Calling Sequence:

　　spec_fft(wavefile);

　　spec_fft(wavefile, window_type);

Parameters:

　　wavefile: wave file. Vector or matrix.

　　window_type: desired window type. Interger.

Description:

This function use one of the methods that estimating the power spectrum.

Examples:

x=wavread('d:\test.wav');

y=spec_fft(x);

y=spec_fft(x, 4);

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　back to top

7．spec_perio

　　----the periodogram spectral estimator.

Calling Sequence:

　　spec_perio(wavefile);

　　spec_perio(wavefile, window_type);

Parameters:

　　wavefile: wave file. Vector or matrix.

　　window_type: desired window type. Interger.

Description:

This function is the periodogram, whcih is one of the classical spectral estimators..

Examples:

x=wavread('d:\test.wav');

y=spec_perio(x);

y=spec_perio(x, 4);

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　back to top