MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches
MayaFlux::Yantra::SpeechSettings Struct Reference

How speech runs are found and measured. More...

#include <SpeechSegmenter.hpp>

Collaboration diagram for MayaFlux::Yantra::SpeechSettings:

Public Attributes

uint32_t max_run { 0 }
 Longest speech interval in samples, 0 for no cap.
bool measure { false }
 Also measure the voiced fraction and pitch of each speech interval.
uint32_t min_silence { 1600 }
 Shortest silence that ends a speech run, in samples.
uint32_t min_speech { 4000 }
 Shortest speech run kept, in samples.
uint32_t padding { 480 }
 Samples added on each side of a speech run.
double threshold { 0.5 }
 Speech probability at or above which speech starts.
double voicing_threshold { 0.5 }
 Periodicity at or above which a window is voiced.

Detailed Description

How speech runs are found and measured.

The scan follows Silero's get_speech_timestamps: a run starts at threshold, ends after min_silence without speech, and is widened by padding on both sides. Runs shorter than min_speech are dropped. max_run caps one speech interval in samples, 0 for no cap. All lengths are in samples at 16 kHz.

With measure on, each speech interval also gets a voiced fraction and a pitch from the waveform windows whose start lies in it. A window is voiced when its periodicity, divided by the share of pairs its lag can pair, is at least voicing_threshold. The threshold is a starting choice, not a measured one.

Definition at line 37 of file SpeechSegmenter.hpp.


The documentation for this struct was generated from the following file: