Note:
This bibliographic page is archived and will no longer be updated.
For an up-to-date list of publications from the Music Technology Group see the
Publications list
.
Training neural audio classifiers with few data
| Title | Training neural audio classifiers with few data |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Conference Name | 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2019) |
| Authors | Pons, J. , Serrà J. , & Serra X. |
| Conference Location | Brighton, UK |
| Abstract | We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical networks, (iii) transfer learning, or (iv) their combination, can foster deep learning models to better leverage a small amount of training examples. To this end, we evaluate (i-iv) for the tasks of acoustic event recognition and acoustic scene classification, considering from 1 to 100 labeled examples per class. Results indicate that transfer learning is a powerful strategy in such scenarios, but prototypical networks show promising results when one does not count with external or validation data. |
| preprint/postprint document | https://arxiv.org/abs/1810.10274 |
Additional material:
