MTG / essentia

C++ library for audio and music analysis, description and synthesis, including Python bindings
http://essentia.upf.edu
GNU Affero General Public License v3.0
2.82k stars 527 forks source link

speech vs music algorithms #1406

Closed flckv closed 4 months ago

flckv commented 6 months ago

Hi, could you please list which tools are designed for speech audios, please?

dbogdanov commented 6 months ago

Hi @flckv. Do you have specific analysis task in mind?

Algorithms such as LPC, MFCC compute features commonly used in speech analysis. Also pitch detection algorthims can be relevant.

flckv commented 6 months ago

hi @dbogdanov, thank you for followup. I am interested in detecting the speech onset automatically, specifically the beat of speech.

dbogdanov commented 6 months ago

For onsets detection, Essentia provides various detection methods that might be useful: https://essentia.upf.edu/tutorial_rhythm_onsetdetection.html https://essentia.upf.edu/reference/std_OnsetDetection.html https://essentia.upf.edu/reference/std_OnsetDetectionGlobal.html https://essentia.upf.edu/reference/std_SuperFluxExtractor.html