Results

Results are shown below for both the open and closed set evaluation. For RMSE scores, small values are best. For correlation coefficients (corr), large numbers are best. The table also identifies which systems are intrusive and which are non-intrusive. The system labeled 'prior' simply returns the training set average sentence intelligibility for all sentences.

Team	Paper	Intrusive?	RMSE (closed)	Corr (closed)	RMSE (open)	Corr (open)
E30	[paper]	Yes	22.5	0.79	--	--
E32	[paper]	Yes	23.1	0.77	23.5	0.76
E29	[paper]	No	23.3	0.77	24.6	0.73
E36	[paper]	Yes	24.0	0.76	29.2	0.60
E33	[paper]	No	24.1	0.75	28.9	0.65
E16	[paper]	No	24.7	0.74	30.7	0.59
E22	[paper]	No	25.9	0.70	32.1	0.54
E19	[paper]	Yes	27.5	0.66	28.1	0.63
Baseline		Yes	28.5	0.62	36.5	0.53
E06	[paper]	No	32.0	0.50	--	--
E34	[paper]	No	33.4	0.43	--	--
E35	[paper]	No	35.4	0.25	35.7	0.22
Prior		No	36.4	--	36.2	--
E31	[paper]	Yes	37.2	0.41	28.3	0.67
E23	[paper]	No	41.5	0.07	43.7	0.05
E02	[paper]	Yes	--	--	35.2	0.38
E38	[paper]	Yes	--	--	49.7	0.30

Prizes

The Hearing Industry Research Consortium best system prizes were awarded to

1st place: Zezario et al, MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids for best performance for a non-intrusive system,
2nd place: Huckvale et al, ELO-SPHERES Intelligibility Prediction Model for the Clarity Prediction Challenge 2022 for best performance of an intrusive system,
3rd place: Röttges et al., Speech Intelligibility Prediction for Hearing-Impaired Listeners with the bBSIM-STI Model for best performance in the open-set track.

(Systems E029 and E032 were not eligible for prizes due to links with the organisers.)

The Hearing Industry Research Consortium student prizes were awarded to

1st place: Ryandhimas Zezario from the National Taiwan University,
2nd place: Franklin Yohan Alvarez Cardinale from Medizinische Hochschule Hannover, Germany
3rd place: Jana Rossbach from Carl von Ossietzky University, Oldenburg, Germany.

Congratulations to the winners!

[TOP]