facebookresearch / EasyComDatasetLinks
The Easy Communications (EasyCom) dataset is a world-first dataset designed to help mitigate the *cocktail party effect* from an augmented-reality (AR) -motivated multi-sensor egocentric world view.
☆119Updated last year
Alternatives and similar repositories for EasyComDataset
Users that are interested in EasyComDataset are comparing it to the libraries listed below
Sorting:
- Codebase for the paper "Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation" (ECCV2020)☆72Updated 4 years ago
- Baseline method for audio-visual sound event localization and detection task of DCASE 2023 challenge☆52Updated 3 months ago
- VoViT: Low Latency Graph-based Audio-Visual VoiceSeparation Transformer☆34Updated 2 years ago
- Implementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch☆74Updated 3 years ago
- Repo for Visual Acoustic Matching, CVPR 2022☆67Updated 2 years ago
- Public Code for the paper MAE-AST: Masked Autoencoding Audio Spectrogram Transformer☆87Updated 3 years ago
- Code for paper Learning Audio-Visual Dereverberation☆29Updated 2 years ago
- Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations", ICASSP 2021.☆92Updated 2 years ago
- ☆41Updated 2 years ago
- N/A☆174Updated 3 years ago
- COLA contrastive pre-training method implemented in PyTorch☆43Updated 4 years ago
- ☆45Updated 2 years ago
- CP-JKU submission to DCASE 19, performant single-model CNN