Correction to: Universal Access in the Information Society https://doi.org/10.1007/s10209-023-00992-1

In this article the incorrect Fig. 7 appear as below:

figure a

The Fig. 7 should have appeared as shown below.

Fig. 7
figure 7

Transformers tend to outperform RNNs on different SLT tasks in terms of BLEU-4 score on the RWTH-PHOENIX-Weather 2014T dataset

Full size image

In this article the incorrect Fig. 8 appear as below:

figure b

The Fig. 8 should have appeared as shown below.

Fig. 8
figure 8

Evolution of model scores on the RWTH-PHOENIX-Weather 2014T per task

Full size image

In this article the incorrect Table 6 appear as below:

figure c

The Table 6 should have appeared as shown below.

figure d

The Table 7 appears incorrectly as below.

figure e

The correct Table 7 should be shown as below.

figure f

This erratum contains changes to the findings from two of the cited papers. For citations [88] and [99]:

[88] Chen, Y., Zuo, R., Wei, F., Wu, Y., Liu, S., & Mak, B.: Two-stream network for sign language recognition and translation. Advances in Neural Information Processing Systems, 35, 17043–17056 (2022)

[99] Chen, Y., Wei, F., Sun, X., Wu, Z., Lin, S.: A simple multi-modality transfer learning baseline for sign language translation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5120–5130 (2022)

The original article has been corrected.