Name
Title | ||
|---|---|---|
A closer look at deep learning neural networks with low-level spectral periodicity features |
Abstract | ||
|---|---|---|
Systems built using deep learning neural networks trained on low-level spectral periodicity features (DeSPerF) reproduced the most “ground truth” of the systems submitted to the MIREX 2013 task, “Audio Latin Genre Classification.” To answer why this was the case, we take a closer look at the behavior of a DeSPerF system we create and evaluate using the benchmark dataset BALLROOM. We find through time stretching that this DeSPerF system appears to obtain a high figure of merit on the task of music genre recognition because of a confounding of tempo with “ground truth” in BALLROOM. This observation motivates several predictions. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/CIP.2014.6844511 | CIP |
Keywords | DocType | ISSN |
audio signal processing,learning (artificial intelligence),music,neural nets,desperf system,mirex 2013 task,audio latin genre classification,benchmark dataset ballroom,deep learning neural networks,figure of merit,ground truth,low-level spectral periodicity features,music genre recognition,time stretching | Conference | 2327-1671 |
Citations | PageRank | References |
3 | 0.41 | 6 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bob L. Sturm | 1 | 241 | 29.88 |
| Corey Kereliuk | 2 | 13 | 1.92 |
| aggelos pikrakis | 3 | 3 | 0.41 |