Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing
Figure 1 | EURASIP Journal on Audio, Speech, and Music Processing

Figure 1

From: The self-taught vocal interface

Figure 1

A schematic overview of the learning framework. Two data streams containing acoustic (lower part) and semantic (upper part) features are enhanced and processed in the direction of the arrows towards the centre where they are combined using NMF.

Back to article page