SPTVMod - Fast-LFO Dataset Spectrograms

This page presents the output spectrograms of the models trained in Experiment 2 using the 4 s long chirp-train input signal. Multiple models were trained for each combination of mode seeking hyperparameters (λ, ε) and each dataset. We inspect the results obtained after the adversarial phase, then after the fine-tuning phase.

λ = 0 means that mode seeking is disabled.

The spectrograms use boxcar chirp-aligned windows, i.e. the window and hop sizes are equal to the chirp length (1336 samples); the frequency axis ranges from 0.04 to 17 kHz in log-scale.

To find a figure that is part of the paper, please use your browser's search tool to find the text "Figure xy" (e.g. "Figure 8g").

Model	Adversarial Phase Checkpoint: best modulation loss	Spectral Fine-tuning (no SPN pre-training) Checkpoint: best modulation loss	Spectral Fine-tuning (no SPN pre-training) Checkpoint: best spectral loss	Spectral Fine-tuning (with SPN pre-training) Checkpoint: best modulation loss	Spectral Fine-tuning (with SPN pre-training) Checkpoint: best spectral loss
1 λ=0.01 ε=0.001
2 λ=0.01 ε=0.01
3 λ=0.01 ε=0.1
4 λ=0.1 ε=0.001	Figure 8o
5 λ=0.1 ε=0.01	Figure 8n
6 λ=0.1 ε=0.1
7 λ=1.0 ε=0.001
8 λ=1.0 ε=0.01	Figure 8m
9 λ=1.0 ε=0.1
10 λ=0
11 λ=0.01 ε=0.01
12 λ=0	Figure 8j
13 λ=0.01 ε=0.001
14 λ=0.01 ε=0.01
15 λ=0.01 ε=0.1				Figure 9o
16 λ=0.1 ε=0.001
17 λ=0.1 ε=0.01
18 λ=0.1 ε=0.1
19 λ=1.0 ε=0.001
20 λ=1.0 ε=0.01
21 λ=1.0 ε=0.1
22 λ=0
23 λ=0.01 ε=0.01
24 λ=0	Figure 8p
25 λ=0.01 ε=0.001
26 λ=0.01 ε=0.01
27 λ=0.01 ε=0.1
28 λ=0.1 ε=0.001
29 λ=0.1 ε=0.01
30 λ=0.1 ε=0.1
31 λ=1.0 ε=0.001
32 λ=1.0 ε=0.01
33 λ=1.0 ε=0.1	Figure 8k
34 λ=0
35 λ=0.01 ε=0.01
36 λ=0
37 λ=0			Figure 9m	Figure 9n	Figure 9l
38 λ=0	Figure 8l
39 λ=0
40 λ=0
41 λ=0
42 λ=0

Reference (Target Effect's Output)