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

EURASIP Journal on Audio, Speech, and Music Processing

Table 1 Summary of data used during training and evaluation

Data split	Number of rooms	Number of BRIRs	Total generated samples
Real training set	40	671	35,000
Augmented training set	-	20,000	200,000
Evaluation set	7	100	1000