CMSIS-DSP  
CMSIS DSP Software Library
 
Loading...
Searching...
No Matches

Functions

arm_status arm_mfcc_init_q31 (arm_mfcc_instance_q31 *S, uint32_t fftLen, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Generic initialization of the MFCC Q31 instance structure.
 
arm_status arm_mfcc_init_32_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 32 sample MFCC.
 
arm_status arm_mfcc_init_64_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 64 sample MFCC.
 
arm_status arm_mfcc_init_128_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 128 sample MFCC.
 
arm_status arm_mfcc_init_256_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 256 sample MFCC.
 
arm_status arm_mfcc_init_512_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 512 sample MFCC.
 
arm_status arm_mfcc_init_1024_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 1024 sample MFCC.
 
arm_status arm_mfcc_init_2048_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 2048 sample MFCC.
 
arm_status arm_mfcc_init_4096_q31 (arm_mfcc_instance_q31 *S, uint32_t nbMelFilters, uint32_t nbDctOutputs, const q31_t *dctCoefs, const uint32_t *filterPos, const uint32_t *filterLengths, const q31_t *filterCoefs, const q31_t *windowCoefs)
 Initialization of the MFCC Q31 instance structure for 4096 sample MFCC.
 
arm_status arm_mfcc_q31 (const arm_mfcc_instance_q31 *S, q31_t *pSrc, q31_t *pDst, q31_t *pTmp)
 MFCC Q31.
 

Description

Function Documentation

◆ arm_mfcc_init_1024_q31()

arm_status arm_mfcc_init_1024_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 1024 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_128_q31()

arm_status arm_mfcc_init_128_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 128 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_2048_q31()

arm_status arm_mfcc_init_2048_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 2048 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_256_q31()

arm_status arm_mfcc_init_256_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 256 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_32_q31()

arm_status arm_mfcc_init_32_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 32 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_4096_q31()

arm_status arm_mfcc_init_4096_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 4096 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_512_q31()

arm_status arm_mfcc_init_512_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 512 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_64_q31()

arm_status arm_mfcc_init_64_q31 ( arm_mfcc_instance_q31 S,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Initialization of the MFCC Q31 instance structure for 64 sample MFCC.

Parameters
[out]Spoints to the mfcc instance structure
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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.

◆ arm_mfcc_init_q31()

arm_status arm_mfcc_init_q31 ( arm_mfcc_instance_q31 S,
uint32_t  fftLen,
uint32_t  nbMelFilters,
uint32_t  nbDctOutputs,
const q31_t dctCoefs,
const uint32_t *  filterPos,
const uint32_t *  filterLengths,
const q31_t filterCoefs,
const q31_t windowCoefs 
)

Generic initialization of the MFCC Q31 instance structure.

Parameters
[out]Spoints to the mfcc instance structure
[in]fftLenfft length
[in]nbMelFiltersnumber of Mel filters
[in]nbDctOutputsnumber of Dct outputs
[in]dctCoefspoints to an array of DCT coefficients
[in]filterPospoints of the array of filter positions
[in]filterLengthspoints to the array of filter lengths
[in]filterCoefspoints to the array of filter coefficients
[in]windowCoefspoints 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 CMSIS-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.

◆ arm_mfcc_q31()

arm_status arm_mfcc_q31 ( const arm_mfcc_instance_q31 S,
q31_t pSrc,
q31_t pDst,
q31_t pTmp 
)

MFCC Q31.

Parameters
[in]Spoints to the mfcc instance structure
[in]pSrcpoints to the input samples in Q31
[out]pDstpoints to the output MFCC values in q8.23 format
[in,out]pTmppoints to a temporary buffer of complex
Returns
error status
Description
The number of input samples is the FFT length used when initializing the instance data structure.

The temporary buffer has a 2*fft length.

The source buffer is modified by this function.

The function may saturate. If the FFT length is too big and the number of MEL filters too small then the fixed point computations may saturate.