MFCC Transform. More...

Modules
	MFCC F32

	MFCC F16

	MFCC Q15

	MFCC Q31

Macros
#define	MFCC_INIT_F32(LEN)

Functions
riscv_status	riscv_mfcc_init_f32 (riscv_mfcc_instance_f32 S, uint32_t fftLen, uint32_t nbMelFilters, uint32_t nbDctOutputs, const float32_t dctCoefs, const uint32_t filterPos, const uint32_t filterLengths, const float32_t filterCoefs, const float32_t windowCoefs)
	Generic initialization of the MFCC F32 instance structure. More...

	MFCC_INIT_F32 (32)
	Initialization of the MFCC F32 instance structure for 32 samples MFCC. More...

	MFCC_INIT_F32 (64)
	Initialization of the MFCC F32 instance structure for 64 samples MFCC. More...

	MFCC_INIT_F32 (128)
	Initialization of the MFCC F32 instance structure for 128 samples MFCC. More...

	MFCC_INIT_F32 (256)
	Initialization of the MFCC F32 instance structure for 256 samples MFCC. More...

	MFCC_INIT_F32 (512)
	Initialization of the MFCC F32 instance structure for 512 samples MFCC. More...

	MFCC_INIT_F32 (1024)
	Initialization of the MFCC F32 instance structure for 1024 samples MFCC. More...

	MFCC_INIT_F32 (2048)
	Initialization of the MFCC F32 instance structure for 2048 samples MFCC. More...

	MFCC_INIT_F32 (4096)
	Initialization of the MFCC F32 instance structure for 4096 samples MFCC. More...

Detailed Description

MFCC Transform.

There are separate functions for floating-point, Q15, and Q31 data types.

Macro Definition Documentation

◆ MFCC_INIT_F32

#define MFCC_INIT_F32 ( LEN )

Function Documentation

◆ MFCC_INIT_F32() [1/8]

MFCC_INIT_F32 ( 1024 )

Initialization of the MFCC F32 instance structure for 1024 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ MFCC_INIT_F32() [2/8]

MFCC_INIT_F32 ( 128 )

Initialization of the MFCC F32 instance structure for 128 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ MFCC_INIT_F32() [3/8]

MFCC_INIT_F32 ( 2048 )

Initialization of the MFCC F32 instance structure for 2048 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ MFCC_INIT_F32() [4/8]

MFCC_INIT_F32 ( 256 )

Initialization of the MFCC F32 instance structure for 256 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ MFCC_INIT_F32() [5/8]

MFCC_INIT_F32 ( 32 )

Initialization of the MFCC F32 instance structure for 32 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ MFCC_INIT_F32() [6/8]

MFCC_INIT_F32 ( 4096 )

Initialization of the MFCC F32 instance structure for 4096 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ MFCC_INIT_F32() [7/8]

MFCC_INIT_F32 ( 512 )

Initialization of the MFCC F32 instance structure for 512 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ MFCC_INIT_F32() [8/8]

MFCC_INIT_F32 ( 64 )

Initialization of the MFCC F32 instance structure for 64 samples MFCC.

Parameters

[out]	S	points to the mfcc instance structure
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

◆ riscv_mfcc_init_f32()

riscv_status riscv_mfcc_init_f32	(	riscv_mfcc_instance_f32 *	S,
		uint32_t	fftLen,
		uint32_t	nbMelFilters,
		uint32_t	nbDctOutputs,
		const float32_t *	dctCoefs,
		const uint32_t *	filterPos,
		const uint32_t *	filterLengths,
		const float32_t *	filterCoefs,
		const float32_t *	windowCoefs
	)

Generic initialization of the MFCC F32 instance structure.

Parameters

[out]	S	points to the mfcc instance structure
[in]	fftLen	fft length
[in]	nbMelFilters	number of Mel filters
[in]	nbDctOutputs	number of Dct outputs
[in]	dctCoefs	points to an array of DCT coefficients
[in]	filterPos	points of the array of filter positions
[in]	filterLengths	points to the array of filter lengths
[in]	filterCoefs	points to the array of filter coefficients
[in]	windowCoefs	points to the array of window coefficients

Returns: error status

Description: The matrix of Mel filter coefficients is sparse. Most of the coefficients are zero. To avoid multiplying the spectrogram by those zeros, the filter is applied only to a given position in the spectrogram and on a given number of FFT bins (the filter length). It is the reason for the arrays filterPos and filterLengths.

window coefficients can describe (for instance) a Hamming window. The array has the same size as the FFT length.

The folder Scripts is containing a Python script which can be used to generate the filter, dct and window arrays.

: This function should be used only if you don't know the FFT sizes that you'll need at build time. The use of this function will prevent the linker from removing the FFT tables that are not needed and the library code size will be bigger than needed.

: If you use NMSIS-DSP as a static library, and if you know the MFCC sizes that you need at build time, then it is better to use the initialization functions defined for each MFCC size.

Modules

Macros

Functions

Detailed Description

Macro Definition Documentation

◆ MFCC_INIT_F32

Function Documentation

◆ MFCC_INIT_F32() [1/8]

◆ MFCC_INIT_F32() [2/8]

◆ MFCC_INIT_F32() [3/8]

◆ MFCC_INIT_F32() [4/8]

◆ MFCC_INIT_F32() [5/8]

◆ MFCC_INIT_F32() [6/8]

◆ MFCC_INIT_F32() [7/8]

◆ MFCC_INIT_F32() [8/8]

◆ riscv_mfcc_init_f32()