Skip to main content

Table 3 SER, error per class and average class error for the RNN classifier on the test partition for the best frontend configurations and different number of stacked BLSTM layers

From: Multiclass audio segmentation based on recurrent neural networks for broadcast domain data

LayersSERClass error (%)Avg
1 BLSTM16.2516.8230.0026.7532.0726.41
2 BLSTM15.9116.2828.8226.3231.9425.84
3 BLSTM16.0215.7127.4630.0930.7426.00