FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

Last update: Dec 22, 2022

Overview

FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating roomimpulse 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.

Requirements

Python3.6
Pytorch
python-dateutil
easydict
pandas
torchfile
gdown
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
   
    <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

Generete RIRs using trained model

Download the trained model using this command

source download_generate.sh

Create normalized embeddings list in pickle format. You can run following command to generate an example embedding list

 python3 example1.py

Run the following command inside code_new to generate RIRs corresponding to the normalized embeddings list. You can find generated RIRs inside code_new/Generated_RIRs

python3 main.py --cfg cfg/RIR_eval.yml --gpu 0

Range

Our trained NN-DAS is capable of generating RIRs with the following range accurately.

Room Dimension X --> 8m to 11m
Room Dimesnion Y --> 6m to 8m
Room Dimension Z --> 2.5m to 3.5m
Listener Position --> Any position within the room
Speaker Position --> Any position within the room
Reverberation time --> 0.2s to 0.7s

Training the Model

Run the following command to download the training dataset we created using a Diffuse Acoustic Simulator. You also can train the model using your dataset.

source download_data.sh

Run the following command to train the model. You can pass what GPUs to be used for training as an input argument. In this example, I am using 2 GPUs.

python3 main.py --cfg cfg/RIR_s1.yml --gpu 0,1

Related Works

Citations

If you use our FAST-RIR for your research, please consider citing

@misc{ratnarajah2021fastrir,
      title={FAST-RIR: Fast neural diffuse room impulse response generator}, 
      author={Anton Ratnarajah and Shi-Xiong Zhang and Meng Yu and Zhenyu Tang and Dinesh Manocha and Dong Yu},
      year={2021},
      eprint={2110.04057},
      archivePrefix={arXiv},
      primaryClass={cs.SD}
}

Our work is inspired by

@inproceedings{han2017stackgan,
Author = {Han Zhang and Tao Xu and Hongsheng Li and Shaoting Zhang and Xiaogang Wang and Xiaolei Huang and Dimitris Metaxas},
Title = {StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks},
Year = {2017},
booktitle = {{ICCV}},
}

If you use our training dataset generated using Diffuse Acoustic Simulator in your research, please consider citing

@inproceedings{9052932,
  author={Z. {Tang} and L. {Chen} and B. {Wu} and D. {Yu} and D. {Manocha}},  
  booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},  
  title={Improving Reverberant Speech Training Using Diffuse Acoustic Simulation},   
  year={2020},  
  volume={},  
  number={},  
  pages={6969-6973},
}

FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

Related tags

Overview

FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

Requirements

Embedding

Generete RIRs using trained model

Range

Training the Model

Related Works

Citations

Owner

Anton Jeran Ratnarajah

Xview3 solution - XView3 challenge, 2nd place solution

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Self-supervised learning optimally robust representations for domain generalization.

Pytorch Lightning Implementation of SC-Depth Methods.

Implementation for Curriculum DeepSDF

Deep Distributed Control of Port-Hamiltonian Systems

Objective of the repository is to learn and build machine learning models using Pytorch. 30DaysofML Using Pytorch

[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

SpinalNet: Deep Neural Network with Gradual Input

Structured Edge Detection Toolbox

Metrics to evaluate quality and efficacy of synthetic datasets.

A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population

Multi-resolution SeqMatch based long-term Place Recognition

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Lacmus is a cross-platform application that helps to find people who are lost in the forest using computer vision and neural networks.

A computational optimization project towards the goal of gerrymandering the results of a hypothetical election in the UK.

Megaverse is a new 3D simulation platform for reinforcement learning and embodied AI research

An official TensorFlow implementation of “CLCC: Contrastive Learning for Color Constancy” accepted at CVPR 2021.

[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

Deep Image Matting implementation in PyTorch