Results

The 2nd Clarity Enhancement Challenge is now complete. Results are shown below along with links to the system description papers. Further information can be found on the Clarity-CEC2-2022 workshop website here.

The table below reports both the HASPI and listener intelligibility scores for all the submitted systems. The column 'Spkr. ID' and 'Head Rot.' indicate whether systems made use of the speaker identity and head rotation information, respectively. Links to the system reports are also provided.

Rank	Team	ID	Paper	Spkr. ID	Head Rot.	HASPI	Listener
1	T01	E009	Link			0.966	91.5
2	T02	E031	Link	Yes		0.801	78.1
3	T03	E008_hr	Link		Yes	0.784	52.8
4	T03	E008	Link			0.777
5	T04	E037	Link			0.775	69.4
6	T04	E022	Link			0.721	64.8
7	T05	E024_hr	Link		Yes	0.63	44.5
8	T05	E024	Link			0.617
9	T06	E036	Link	Yes		0.599	47.9
10	T06	E038	Link	Yes		0.554	34
11	T07	E032	Link	Yes		0.549	36
12	T01	Baseline				0.258	26.5
13	T01	None				0.172

Prizes

The Hearing Industry Research Consortium prizes for systems with the best HASPI score were awarded as follows:

• 1st place: System E009, Cornell et al, Multi-channel Target Speaker Extraction with Refinement: The WAVLAB Submission to the Second Clarity Enhancement Challenge
• 2nd place: System E031, Liu and Zhang, DRC-NET for The 2nd Clarity Enhancement Challenge
• 3rd place: System E008_hr, Ouyang et al., The Orka Inc Entry to the 2nd Clarity Enhancement Challenge

The Hearing Industry Research Consortium prizes for systems providing the best listener intelligibility scores were awarded as follows:

• 1st place: System E009, Cornell et al, Multi-channel Target Speaker Extraction with Refinement: The WAVLAB Submission to the Second Clarity Enhancement Challenge
• 2nd place: System E031, Liu and Zhang, DRC-NET for The 2nd Clarity Enhancement Challenge
• 3rd place: System E037, Lei et al., The Nanjing University / Horizon Robotics system for the 2nd Clarity Enhancement Challenge

Congratulations to the winners!