#include <map>
#include <string>
#include "matrix/matrix-lib.h"
#include "util/common-utils.h"
#include "base/kaldi-error.h"
Go to the source code of this file.
|
| kaldi |
| This code computes Goodness of Pronunciation (GOP) and extracts phone-level pronunciation feature for mispronunciations detection tasks, the reference:
|
|
|
int32 | NumFrames (int64 num_samples, const FrameExtractionOptions &opts, bool flush=true) |
| This function returns the number of frames that we can extract from a wave file with the given number of samples in it (assumed to have the same sampling rate as specified in 'opts'). More...
|
|
int64 | FirstSampleOfFrame (int32 frame, const FrameExtractionOptions &opts) |
|
void | Dither (VectorBase< BaseFloat > *waveform, BaseFloat dither_value) |
|
void | Preemphasize (VectorBase< BaseFloat > *waveform, BaseFloat preemph_coeff) |
|
void | ProcessWindow (const FrameExtractionOptions &opts, const FeatureWindowFunction &window_function, VectorBase< BaseFloat > *window, BaseFloat *log_energy_pre_window=NULL) |
| This function does all the windowing steps after actually extracting the windowed signal: depending on the configuration, it does dithering, dc offset removal, preemphasis, and multiplication by the windowing function. More...
|
|
void | ExtractWindow (int64 sample_offset, const VectorBase< BaseFloat > &wave, int32 f, const FrameExtractionOptions &opts, const FeatureWindowFunction &window_function, Vector< BaseFloat > *window, BaseFloat *log_energy_pre_window) |
|