Fig. 5 | Scientific Reports

Fig. 5

From: Leveraging spatial cues from cochlear implant microphones to efficiently enhance speech separation in naturalistic listening scenes

Fig. 5

Speech separation performance as a function of talker gender pairing and spatial distance for various input configurations. Bars show average SI-SDRi across small (0° and 15°) and large (60° and 90°) talker distances. F–F two female talkers, M–M = two male talkers, F–M one male and one female talker. Asterisks indicate a significant difference between small and large distances (Kruskal–Wallis H tests, FDR corrected: *** = p < 0.0001).

Back to article page