search

TWOEARS / auditory-front-end

Two!Ears Auditory Model - Auditory front-end module
http://docs.twoears.eu/en/latest/afe/
GNU General Public License v2.0
16 stars 10 forks source link

Use AFE to replicate van Dorp Schuitman model #17

Closed hagenw closed 7 years ago

hagenw commented 7 years ago

This tries to implement the model described in [1] by using the AFE.

The model is currently implemented as the function afeRAA() under test/Development_test_scripts/.

[1] van Dorp Schuitman, J., de Vries, D., & Lindau, A. (2013), "Deriving content-specific measures of room acoustic perception using a binaural, nonlinear auditory model," The Journal of the Acoustical Society of America, 133(March), 1572–1585.

hagenw commented 7 years ago

@ryanckim: besides adding new functions for the van Dorp Schuitmann model you also changed the adaptation processor adaptationProc(). Could you shortly describe what you changed there and if this can have an influence on other parts of the AFE?

Hardcorehobel commented 7 years ago

It seems that the room acoustic analyzer (RAA) is a standalone program placed in test\afeRAA. If this function is supposed to be used, I would rather place it in tools and provide a simple demo script, even if that demo is only loading a file and calling afeRAA directly. Otherwise, the visibility of this function is so low that it may not be used at all. What do you think @ryanckim @hagenw ?

hagenw commented 7 years ago

That sounds good. The original idea was to implement it as a processor, but there was not enough time, so it was implemented as a separate function. But I agree, that it is not only a test function and we should move it to a more prominent place. tools would be fine with me.

Hardcorehobel commented 7 years ago

ok, who's going to do it?

hagenw commented 7 years ago

I will do it.

Hardcorehobel commented 7 years ago

Cool, do you mind creating a little DEMO_RAA, which essentially loads a speech signal and triggers afeRAA?