From: Multi-rate modulation encoding via unsupervised learning for audio event detection
 | Condition | PSDS1 | PSDS2 |
---|---|---|---|
 | avg \(\varvec{\pm }\) std | avg \(\varvec{\pm }\) std | |
1\(\times\)CRNN | \(f_c\) = 0.8 Hz | 0.361 ± 0.007 | 0.601 ± 0.007 |
\(f_c\) = 2.4 Hz | 0.371 ± 0.006 | 0.603 ± 0.002 | |
\(f_c\) = 4 Hz | 0.365 ± 0.005 | 0.593 ± 0.008 | |
VAE | 0.365 ± 0.003 | 0.605 ± 0.004 | |
2\(\times\)CRNN | \(f_{c1}\) = 0.8 Hz | 0.368 ± 0.004 | 0.612 ± 0.007 |
\(f_{c2}\)Â = 2.4 Hz | |||
\(f_{c1}\) = 0.8 Hz | 0.365 ± 0.003 | 0.594 ± 0.003 | |
\(f_{c2}\)Â = 4 Hz | |||
\(f_{c1}\) = 2.4 Hz, | 0.374 ± 0.009 | 0.611± 0.009 | |
\(f_{c2}\)Â = 4 Hz | |||
3\(\times\)CRNN | Low-pass only | 0.373 ± 0.007 | 0.607 ± 0.005 |
High-pass only | 0.376 ± 0.007 | 0.613 ± 0.008 |