You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
Since I am a beginner in and Audio and 3D, if you don't mind, I have some questions (that might be evident for you):
You said that
Receiver positions are therefore the same at all times. The tranmitter is the in the origin of the coordinate system and, from the receiver's perspective, x points forward, y points right, and z points up. <
I took a look at the dataset, I guess that rx_positions is the positions of the receiver and tx_positions is the positions of the sound transmitter. If the origin of the coordinate system is in the transmitter, then why rx_positions are all zeros in (x,y,z) ?
My another question is about the network, will you release the pretrained model? If not, can the provided training code produce similar outstanding results?
And how the network generalizes, like for example, what if I change the mono-audio and the positions during inference? I have monoaudio and 3d positions of my own but I cannot finetune the model because I dont have ground-truth binaural audio.
Thanks for your reply and again great work!
The text was updated successfully, but these errors were encountered:
Hi, thanks for you great work!
Since I am a beginner in and Audio and 3D, if you don't mind, I have some questions (that might be evident for you):
You said that
I took a look at the dataset, I guess that rx_positions is the positions of the receiver and tx_positions is the positions of the sound transmitter. If the origin of the coordinate system is in the transmitter, then why rx_positions are all zeros in (x,y,z) ?
My another question is about the network, will you release the pretrained model? If not, can the provided training code produce similar outstanding results?
And how the network generalizes, like for example, what if I change the mono-audio and the positions during inference? I have monoaudio and 3d positions of my own but I cannot finetune the model because I dont have ground-truth binaural audio.
Thanks for your reply and again great work!
The text was updated successfully, but these errors were encountered: