lib_vnr feature extraction #defines and data structure definitions

group vnr_features_state

Defines

VNR_PROC_FRAME_LENGTH

Time domain samples block length used internally in VNR DFT computation. NOT USER MODIFIABLE.

<>

VNR_FRAME_ADVANCE

VNR new samples frame size This is the number of samples of new data that the VNR processes every frame. 240 samples at 16kHz is 15msec. NOT USER MODIFIABLE.

VNR_FD_FRAME_LENGTH

Number of bins of spectrum data computed when doing a DFT of a VNR_PROC_FRAME_LENGTH length time domain vector. The VNR_FD_FRAME_LENGTH spectrum values represent the bins from DC to Nyquist. NOT USER MODIFIABLE.

struct vnr_input_state_t

#include <vnr_features_state.h>

VNR form_input state structure.

Public Members

int32_t prev_input_samples[VNR_PROC_FRAME_LENGTH - VNR_FRAME_ADVANCE]

Previous frame time domain input samples which are combined with VNR_FRAME_ADVANCE new samples to form the VNR input frame.

struct vnr_feature_config_t

#include <vnr_features_state.h>

VNR feature extraction config structure.

Public Members

int32_t enable_highpass

Enable highpass filtering of VNR MEL filter output. Disabled by default

struct vnr_feature_state_t

#include <vnr_features_state.h>

State structure used in VNR feature extraction.

Public Members

int32_t feature_buffers[VNR_PATCH_WIDTH][VNR_MEL_FILTERS]

Feature buffer containing the most recent VNR_MEL_FILTERS frames’ MEL frequency spectrum.