Skip to main content
Fig. 8 | EURASIP Journal on Audio, Speech, and Music Processing

Fig. 8

From: Unsupervised adaptation of PLDA models for broadcast diarization

Fig. 8

Schematic for unsupervised independent adaptation for the episodes n−1, n, and n+1. \(\mathcal {M}_{\text {OOD}}\) represents the out-of-domain model and \(\mathcal {M}_{n-1}, \mathcal {M}_{n}\), and \(\mathcal {M}_{n+1}\), and the adapted models for each episode. Φn−1,Φn and Φn+1 are the i-vectors from each episode

Back to article page