Spectral audio descriptors

Typedefs
typedef struct SDTSpectralFeats	SDTSpectralFeats
	Opaque data structure for a spectral features extractor.
typedef struct SDTSpectralFeats	SDTSpectralFeats
	Opaque data structure for a spectral features extractor.

Functions
SDTSpectralFeats *	SDTSpectralFeats_new (unsigned int size)
	Instantiates a spectral features extractor. More...
void	SDTSpectralFeats_free (SDTSpectralFeats *x)
	Destroys a spectral features extractor. More...
void	SDTSpectralFeats_setOverlap (SDTSpectralFeats *x, double f)
	Sets the analysis window overlapping ratio. Accepted values go from 0.0 to 1.0, with 0.0 meaning no overlap and 1.0 meaning total overlap. More...
void	SDTSpectralFeats_setMinFreq (SDTSpectralFeats *x, double f)
	Sets the lower frequency bound for spectral analysis. Spectral bins below this frequency are ignored in the audio descriptors computation. More...
void	SDTSpectralFeats_setMaxFreq (SDTSpectralFeats *x, double f)
	Sets the upper frequency bound for spectral analysis. Spectral bins above this frequency are ignored in the audio descriptors computation. More...
int	SDTSpectralFeats_dsp (SDTSpectralFeats *x, double *outs, double in)
	Signal processing routine. Call this function for each sample to perform signal analysis. More...

Detailed Description

Spectral features extractor: statistical moments (centroid, spread, skewness, kurtosis), spectral flatness, spectral flux and an onset detection function based on rectified, whitened spectral flux.

Function Documentation

int SDTSpectralFeats_dsp	(	SDTSpectralFeats *	x,
		double *	outs,
		double	in
	)

Signal processing routine. Call this function for each sample to perform signal analysis.

Parameters

[in]	x	Pointer to the instance
[out]	outs	Pointer to an array of seven doubles, containing the algorithm outputs. Array members represent the following information respectively: Spectral centroid, Spectral spread, Spectral skewness, Spectral kurtosis, Spectral flatness, Spectral flux, Onset detection function (rectified and whitened spectral flux).
[in]	in	Input sample

Returns

1 if output available (analysis window full), 0 otherwise

void SDTSpectralFeats_free

(

SDTSpectralFeats *

x

)

Destroys a spectral features extractor.

Parameters

[in]

x

Pointer to the instance to destroy

SDTSpectralFeats * SDTSpectralFeats_new

(

unsigned int

size

)

Instantiates a spectral features extractor.

Parameters

[in]

size

Size of the analysis window, in samples

Returns

Pointer to the new instance

void SDTSpectralFeats_setMaxFreq	(	SDTSpectralFeats *	x,
		double	f
	)

Sets the upper frequency bound for spectral analysis. Spectral bins above this frequency are ignored in the audio descriptors computation.

Parameters

[in]	x	Pointer to the instance
[in]	f	Maximum analyzed frequency, in Hz

void SDTSpectralFeats_setMinFreq	(	SDTSpectralFeats *	x,
		double	f
	)

Sets the lower frequency bound for spectral analysis. Spectral bins below this frequency are ignored in the audio descriptors computation.

Parameters

[in]	x	Pointer to the instance
[in]	f	Minimum analyzed frequency, in Hz

void SDTSpectralFeats_setOverlap	(	SDTSpectralFeats *	x,
		double	f
	)

Sets the analysis window overlapping ratio. Accepted values go from 0.0 to 1.0, with 0.0 meaning no overlap and 1.0 meaning total overlap.

Parameters

[in]	x	Pointer to the instance
[in]	f	Overlap ratio [0.0, 1.0]