-
Notifications
You must be signed in to change notification settings - Fork 14
Formant modeling and smoothness estimation
Santiago Barreda edited this page May 18, 2020
·
2 revisions
Modeling is relatively basic. More complicated methods may be added later.
The following process is carried out for each of J formants:
-
Time is normalized so that it goes from 0 to 1.
-
Cosine predictors are generated using normalized time. By default up to 5th order predictors are used. This means we can model formant contours faithfully even if they are somewhat wiggly.
-
The formant track is predicted using an OLS regression analysis.
The output of this process is:
-
A set of regression coefficients for each formant, for each vowel.
-
The above can be used to generate predicted formant values for each track.
File Analysis
Folder Analysis
Tools
Details