MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches
SpeechSegmenter.hpp File Reference

Where speech is in a recording, with optionally how voiced each stretch is and its pitch. More...

Include dependency graph for SpeechSegmenter.hpp:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes

struct  MayaFlux::Yantra::SpeechSegmentation
 Record of one SpeechSegmenter run, stored on the output's facets. More...
class  MayaFlux::Yantra::SpeechSegmenter< InputType, OutputType >
 The speech intervals of a whole mono 16 kHz recording. More...
struct  MayaFlux::Yantra::SpeechSegmenterConfig
 Settings of a SpeechSegmenter. More...
struct  MayaFlux::Yantra::SpeechSettings
 How speech runs are found and measured. More...
struct  MayaFlux::Yantra::SpeechVoicing
 Voicing of each interval, as SpeechSegmentation holds it. More...

Namespaces

namespace  MayaFlux
 Main namespace for the Maya Flux audio engine.
namespace  MayaFlux::Yantra

Typedefs

using MayaFlux::Yantra::AudioSpeechSegmenter = SpeechSegmenter<std::vector<Kakshya::DataVariant>, std::vector<Kakshya::DataVariant>>
 Audio: the speech intervals, concatenated.
using MayaFlux::Yantra::RegionSpeechSegmenter = SpeechSegmenter<std::vector<Kakshya::DataVariant>, Kakshya::RegionGroup>
 Regions: one region per speech interval.

Functions

SpeechVoicing MayaFlux::Yantra::measure_voicing (StandardWaveformAnalyzer &analyzer, std::span< const double > samples, const std::vector< std::pair< size_t, size_t > > &speech, double voicing_threshold)
 Voiced share and median frequency of the waveform windows that start in each interval.
IntervalExtractorConfig MayaFlux::Yantra::speech_scan_settings (const SpeechSettings &speech, size_t samples)
 The interval scan settings of speech runs, for a recording of the given length.
std::vector< std::pair< size_t, size_t > > MayaFlux::Yantra::voiced_intervals (StandardWaveformAnalyzer &analyzer, std::span< const double > samples, double threshold, uint32_t hop)
 The stretches of a recording where the waveform is voiced.
WaveformAnalyzerConfig MayaFlux::Yantra::voicing_analyzer_config (double sample_rate, uint32_t hop=256)
 The waveform analyzer settings the voicing measure uses at the given rate and hop.

Detailed Description

Where speech is in a recording, with optionally how voiced each stretch is and its pitch.

Definition in file SpeechSegmenter.hpp.