Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Breakdown of the EMIR dataset.

More »

Table 1 Expand

Fig 1.

EKM architecture used in experiments.

More »

Fig 1 Expand

Fig 2.

Experiment 1: EKM confusion matrices using FilterBank on EMIR.

More »

Fig 2 Expand

Fig 3.

Experiment 1: EKM confusion matrices using MelSpec on EMIR.

More »

Fig 3 Expand

Fig 4.

Experiment 1: EKM confusion matrices using Chroma on EMIR.

More »

Fig 4 Expand

Fig 5.

Experiment 1: EKM confusion matrices using MFCC on EMIR.

More »

Fig 5 Expand

Table 2.

Experiment 1: Recognition accuracies of VGG networks on EMIR using FilterBank, MelSpec, MFCC and Chroma features with 3s samples.

More »

Table 2 Expand

Table 3.

Experiment 2: EKM model accuracy using 1s, 3s and 5s sample lengths, MFCC features and EMIR data.

More »

Table 3 Expand

Fig 6.

Experiment 2: Convergence curve in 250-epoch training.

More »

Fig 6 Expand

Table 4.

Experiment 3: Comparison of EKM with other CNN and LSTM models, all applied to the EMIR dataset.

More »

Table 4 Expand

Table 5.

Statistical significance tests for Experiment 3.

More »

Table 5 Expand