Multi-Format Contrastive Learning of Audio Representations
This work addresses audio representation learning for tasks like classification, showing that multi-format training within a single modality can yield gains similar to multi-modal methods, though it is incremental in approach.
The paper tackled the problem of learning audio representations by using a multi-format contrastive learning strategy that maximizes agreement between raw audio and its spectral representation, achieving state-of-the-art results with a mean average precision of 0.376 on AudioSet and 90.5% accuracy on ESC-50.
Recent advances suggest the advantage of multi-modal training in comparison with single-modal methods. In contrast to this view, in our work we find that similar gain can be obtained from training with different formats of a single modality. In particular, we investigate the use of the contrastive learning framework to learn audio representations by maximizing the agreement between the raw audio and its spectral representation. We find a significant gain using this multi-format strategy against the single-format counterparts. Moreover, on the downstream AudioSet and ESC-50 classification task, our audio-only approach achieves new state-of-the-art results with a mean average precision of 0.376 and an accuracy of 90.5%, respectively.