HIGHLIGHTS
- who: SUNGHYUN KIM and collaborators from the School of Robotics, Kwangwoon University, have published the research: WaveBYOL: Self-Supervised Learning for Audio Representation From Raw Waveforms, in the Journal: (JOURNAL)
- what: The authors propose the WaveBYOL model which can learn general-purpose audio representations directly from raw waveforms based on the bootstrap your own latent (BYOL) approach a Siamese neural network architecture. The authors assess the representations learned by WaveBYOL by conducting experiments with seven audio downstream tasks under both frozen-model evaluation and fine-tuning settings. In the audio domain, recent studies have been . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.