|
MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
|
|
inlinenodiscard |
The stretches of a recording where the waveform is voiced.
| analyzer | Analyzer built from voicing_analyzer_config with the same hop. |
| samples | One channel of samples. |
| threshold | Periodicity at or above which a window is voiced. |
| hop | Hop of the analyzer. Each voiced window stands for the hop samples around its centre. |
Definition at line 143 of file SpeechSegmenter.hpp.
References MayaFlux::Yantra::WaveformAnalyzer< InputType, OutputType >::analyze_waveform(), MayaFlux::Yantra::WaveformAnalysis::channels, MayaFlux::Kinesis::Discrete::intervals_from_window_starts(), MayaFlux::Kinesis::Discrete::merge_intervals(), MayaFlux::Kinesis::Vision::threshold(), and MayaFlux::Yantra::AnalyzerConfig::window_size.
Referenced by MayaFlux::Yantra::PhonemeExtractor< std::vector< Kakshya::DataVariant >, Kakshya::CompositeArray >::find_voiced().