facebookresearch / learning-audio-visual-dereverberation

Code for paper Learning Audio-Visual Dereverberation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Learning Audio-Visual Dereverberation

Motivation

Reverberation from audio reflecting off surfaces and objects in the environment not only degrades the quality of speech for human perception, but also severely impacts the accuracy of automatic speech recognition. Prior work attempts to remove reverberation based on the audio modality only. Our idea is to learn to dereverberate speech from audio-visual observations. The visual environment surrounding a human speaker reveals important cues about the room geometry, materials, and speaker location, all of which influence the precise reverberation effects in the audio stream. We introduce Visually-Informed Dereverberation of Audio (VIDA), an end-to-end approach that learns to remove reverberation based on both the observed sounds and visual scene. In support of this new task, we develop a large-scale dataset that uses realistic acoustic renderings of speech in real-world 3D scans of homes offering a variety of room acoustics. Demonstrating our approach on both simulated and real imagery for speech enhancement, speech recognition, and speaker identification, we show it achieves state-of-the-art performance and substantially improves over traditional audio-only methods.

Citation

If you find this paper and code useful, please cite the following paper:

@arxiv{chen22av_dereverb,
  title     =     {Learning Audio-Visual Dereverberation,
  author    =     {Changan Chen and Wei Sun and David Harwath and Kristen Grauman},
  journal   =     {arXiv},
  year      =     {2022}
}

Installation

Install this repo into pip by running the following command:

pip install -e .

Usage

  1. Training
py vida/trainer.py --model-dir data/models/vida  --num-channel 2 --use-depth --use-rgb --log-mag --no-mask --phase-loss sin --phase-weight 0.1 --use-triplet-loss --exp-decay --triplet-margin 0.5 --mean-pool-visual --overwrite
  1. Evaluation
py vida/evaluator.py --pretrained-path data/models/vida/best_val.pth --num-channel 2  --log-mag --no-mask --est-pred --use-rgb --use-depth --mean-pool-visual --eval-dereverb

Data

See the data page for instructions on how to download the data

Contributing

See the CONTRIBUTING file for how to help out.

License

This repo is CC-BY-NC licensed, as found in the LICENSE file.

About

Code for paper Learning Audio-Visual Dereverberation

License:Other


Languages

Language:Python 100.0%