Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms

no code implementations • 7 Mar 2023 • Ankit Shah, Shuyi Chen, Kejun Zhou, Yue Chen, Bhiksha Raj

Preliminary results show (1) the proposed BECR can incur a more dispersed embedding on the test set, (2) BECR improves the PaSST model without extra computation complexity, and (3) STFT preprocessing outperforms CQT in all tasks we tested.

Zero-Shot Learning