search

Shahabks / myprosody

A Python library for measuring the acoustic features of speech (simultaneous speech, high entropy) compared to ones of native speech.
https://shahabks.github.io/myprosody/
MIT License
236 stars 64 forks source link

Fillers #6

Closed antoninklopp closed 4 years ago

antoninklopp commented 5 years ago

Hi,

I am looking for filler words and filled pauses, like it seems to be mentioned in the documentation. However, when I run the script, I have the impression that the fillers are actually the moments where people speak.

Here is a simple view of the outputed textgrid

class = "IntervalTier" name = "silences" xmin = 0 xmax = 257.9040362811791 intervals: size = 82 intervals [1]: xmin = 0 xmax = 21.536018140589544 text = "sounding" intervals [2]: xmin = 21.536018140589544 xmax = 22.048018140589544 text = "silent" intervals [3]: xmin = 22.048018140589544 xmax = 30.320018140589543 text = "sounding" intervals [4]: xmin = 30.320018140589543 xmax = 30.672018140589543 text = "silent"

Am I not understanding something?

Thanks for your help!

Shahabks commented 4 years ago

Filler words are captured based on the quality and quantity of CV intervals. Your impression for the latter one is right if you mean by "when people speak", silence pulse between syllables