Our new X account is live! Follow @wizwand_team for updates

Visual Speech Recognition on LRS3 low-resource (test)

19.3WER

Serdyuk et al. (2022)

Updated 4d ago

Evaluation Results

Method	Links
Serdyuk et al. (2022) 2022.12		19.3
RAVEn w/ self-training 2022.12		23.8
RAVEn w/ self-training 2022.12		24.8
Serdyuk et al. (2021) 2022.12		25.9
Shi et al. (2022) w/ self-training 2022.12		28.6
Prajwal et al. (2022) 2022.12		30.7
Shi et al. (2022) 2022.12		32.5
RAVEn 2022.12		32.5
Makino et al. (2019) 2022.12		33.6
Ma et al. (2022) 2022.12		34.7
RAVEn 2022.12		40.2
Shi et al. (2022) 2022.12		46.1
RAVEn 2022.12		47
Shi et al. (2022) 2022.12		51.8
Shillingford et al. (2019) 2022.12		55.1
Xu et al. (2020) 2022.12		57.8
Afouras et al. (2018a) 2022.12		58.9
Zhang et al. (2022) 2022.12		67.8
Base model 2022.12		93.4
Large model 2022.12		95.5