NTT Communication Science Laboratories

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

nttcslab

Composing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model

nttcslab

Code for evaluating Japanese pretrained models provided by NTT Ltd.

nttcslab

P2P Distributed deep learning framework that runs on PyTorch.

nttcslab

Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations

nttcslab

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

nttcslab