|
MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
|
Record of one SpeechSegmenter run, stored on the output's facets. More...
#include <SpeechSegmenter.hpp>
Public Attributes | |
| SpeechSegmenterConfig | config |
| Settings the segmentation was produced under. | |
| std::vector< double > | f0 |
| Median frequency of each interval's voiced windows, empty unless measured. | |
| std::vector< std::pair< size_t, size_t > > | speech |
| Speech intervals, half open sample ranges. | |
| std::vector< double > | voiced_fraction |
| Voiced share of each interval's windows, empty unless measured. | |
Record of one SpeechSegmenter run, stored on the output's facets.
speech holds the speech intervals as half open sample ranges. voiced_fraction and f0 are filled only when the run measured, one entry per interval: the share of its windows that are voiced, and the median frequency in Hz of the voiced ones, 0 when none is.
Definition at line 77 of file SpeechSegmenter.hpp.