Setup

This is the same example as the third example with more reverberant walls: the room size is 3x4x3 m and the reverberation time is 0.5sec. Room

Mod-MFCC Based Clusters

CLUSTER 1
CLUSTER 2
BACKGROUND CLUSTER
Mod-MFCC-based Clusters image
Mod-MFCC-based Clusters image
Mod-MFCC-based Clusters image
cluster reference microphone masked reference signal DSB signal
1


2


Speaker Embedding Clusters

CLUSTER 1
CLUSTER 2
BACKGROUND CLUSTER
SpVer Clusters image
SpVer Clusters image
SpVer Clusters image
cluster reference microphone masked reference signal DSB signal
1


2


Discussion

In the more reverberant condition (compared to the third example), the Mod-MFCC based features create a less than ideal cluster for source 1, as well as missing the best SINR microphone for source 2. The speaker embedding based features consistently deliver good (logical) clusters