EURASIP Journal on Audio, Speech, and Music Processing

Table 2 \(RT_{60}\) predictions from AudMobNet [6] at 1 kHz for different input durations samples from ACE challenge

From: An end-to-end approach for blindly rendering a virtual sound source in an audio augmented reality environment

Input duration [s]	MSE	\(\rho\)	Bias
Shorter than 2	0.015	0.86	− 0.019
3	0.018	0.85	− 0.021
4	0.015	0.94	0.018
Longer Than 4	0.012	0.91	0.016

Back to article page