Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 4 The configuration of the synthesis model

From: Neural electric bass guitar synthesis framework enabling attack-sustain-representation-based technique control

Encoder layer

3

Decoder layer

6

Multi-head attention heads

2

Multi-head attention hidden units

128

Feed-forward network

512

Feed-forward networks

9, 1

Max sequence

1000

Max time

96

Max duration

96

Mel spectrum bands

100

Back to article page