. Author manuscript; available in PMC: 2022 Jan 1.

Published in final edited form as: IEEE/ACM Trans Audio Speech Lang Process. 2021 Jan 25;29:2058–2066. doi: 10.1109/taslp.2021.3054302

TABLE V.

Model Trained on Original TIMIT Utterances Tested on Data Convolved with Different MIRs

Model	SNR	LSD	PESQ
Spline	15.48	2.27	2.56
Original	20.18	0.72	3.65
Test on MIR1	12.53	1.38	2.41
Test on MIR2	13.75	0.87	2.99
Average of 20 MIRs	14.76	1.01	2.82