From: Deep semantic learning for acoustic scene classification
Device | Total | Train | Test | (not used in train/test split) |
---|---|---|---|---|
A | 14,400 | 10,215 | 330 | 3855 |
B, C | 1080 | 2\(\times\)750 | 2\(\times\)330 | — |
S1, S2, S3 | 1080 | 3\(\times\)750 | 3\(\times\)330 | — |
S4, S5, S6 | 1080 | — | 3\(\times\)330 | 750 |
Total | 23,040 | 13,965 | 2970 | — |