nttcslab / m2dLinks
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
☆110Updated last year
Alternatives and similar repositories for m2d
Users that are interested in m2d are comparing it to the libraries listed below
Sorting:
- A library built for easier audio self-supervised training, downstream tasks evaluation☆129Updated last year
- EVAR ~ Evaluation package for Audio Representations☆62Updated 2 months ago
- [SLT'24] The official implementation of SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model☆125Updated 10 months ago
- Dataset and baseline code for the VocalSound dataset (ICASSP2022).☆150Updated 2 years ago
- ☆91Updated 3 months ago
- Learning differentiable temporal resolution on time-series data.☆36Updated 2 years ago
- ☆37Updated 3 months ago
- Audio Captioning datasets for PyTorch.☆120Updated last month
- Inference code for PaSST, using the HEAR API.☆32Updated last year
- PAM is a no-reference audio quality metric for audio generation tasks☆72Updated last year
- Official implementation for our paper "Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations"☆40Updated last week
- This repo includes the official implementations of "Fine-tune the pretrained ATST model for sound event detection".☆141Updated 3 weeks ago
- ☆176Updated 8 months ago
- This package aims at simplifying the download of the AudioSet dataset.☆54Updated last month
- Speech Human Evaluation Estimation Toolkit (SHEET)☆99Updated 2 weeks ago
- Single channel speech source separation by diffusion process (ICASSP 2023)☆112Updated last year
- Public Code for the paper MAE-AST: Masked Autoencoding Audio Spectrogram Transformer☆88Updated 3 years ago
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆98Updated last year
- ☆90Updated 10 months ago
- This github repo is for Neurips 2021 and Interspeech 2022 papers on Non-Matching Reference based estimation of speech quality assessment.…☆103Updated 2 years ago
- Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint☆73Updated 2 years ago
- Confidence interval computation for evaluation in machine learning using the bootstrapping approach☆87Updated last year
- ☆55Updated 8 months ago
- A 6-million Audio-Caption Paired Dataset Built with a LLMs and ALMs-based Automatic Pipeline☆181Updated 8 months ago
- [IJCAI 2024] EAT: Self-Supervised Pre-Training with Efficient Audio Transformer☆184Updated 2 months ago
- Expressive Anechoic Recordings of Speech (EARS)☆185Updated last year
- Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations☆92Updated last year
- [ICLR 2025] Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes☆48Updated 2 months ago
- ☆92Updated 2 years ago
- HAAQI-Net is a novel DNN-based non-intrusive method for assessing music audio quality in hearing aid users.☆16Updated 7 months ago