Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing
Fig. 2 | EURASIP Journal on Audio, Speech, and Music Processing

Fig. 2

From: DOA-guided source separation with direction-based initialization and time annotations using complex angular central Gaussian mixture models

Fig. 2

DOA-GSS block diagram. We consider three different ways to make use of DOA knowledge: a DOA-based initialization of the cACGMM parameter estimation (see Section 4.1), extracting time annotations from the initial masks (Section 4.2), or using one mixture component for each discrete DOA (Section 4.3). These can be used independently or jointly

Back to article page