Help:
I shared my data and model to my university google drive. After I graduated I lost access to the account and the data I shared. If anyone still have access to the data downlaoded using the scripts
- https://github.com/anton-jeran/FAST-RIR/blob/main/download_data.sh
- https://github.com/anton-jeran/FAST-RIR/blob/main/download_generate.sh
Please share with me. I will update the Readme and the above script.
FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR (ICASSP 2022)
This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given rectangular acoustic environment. Our model is inspired by StackGAN architecture. The audio examples and spectrograms of the generated RIRs are available here.
NEWS:
1) We have generalized our FAST-RIR to generate RIRs for any 3D indoor scenes represented using meshes. Official code of our network MESH2IR is available.
2) We release Speech2IR estimator. The official code of our network Speech2IR is available.
Requirements
Python3.6
Pytorch
python-dateutil
easydict
pandas
torchfile
gdown
librosa
soundfile
acoustics
wavefile
wavfile
pyyaml==5.4.1
pickle
Embedding
Each normalized embedding is created as follows: If you are using our trained model, you may need to use extra parameter Correction(CRR).
Listener Position = LP
Source Position = SP
Room Dimension = RD
Reverberation Time = T60
Correction = CRR
CRR = 0.1 if 0.5<T60<0.6
CRR = 0.2 if T60>0.6
CRR = 0 otherwise
Embedding = ([LP_X,LP_Y,LP_Z,SP_X,SP_Y,SP_Z,RD_X,RD_Y,RD_Z,(T60+CRR)] /5) - 1