COLA is a self-supervised pretraining method for learning general-purpose audio data representations. Developed by @aaqib_saeed et al.
— François Chollet (@fchollet) October 25, 2020
Paper: https://t.co/AGr9Jo90zh
Code: https://t.co/oIQaHYNh43 (research done with TF/Keras) pic.twitter.com/ATiOaUDLoU