5/24/2023 0 Comments Cybertronian language translator![]() Our findings also demonstrate that end-to-end translation on predicted glosses provides even better performance than translation on ground truth glosses. On the ASLG-PC12 corpus, we report an improvement of over 16 points in BLEU-4. Our methodology improves on the current state-of-the-art by over 5 and 7 points respectively in BLEU-4 score on ground truth glosses and by using an STMC network to predict glosses of the RWTH-PHOENIX-Weather 2014T dataset. ![]() We perform experiments on RWTH-PHOENIX-Weather 2014T, a challenging SLT benchmark dataset of German sign language, and ASLG-PC12, a dataset involving American Sign Language (ASL) recently used in gloss-to-text translation. We report a wide range of experimental results for various Transformer setups and introduce the use of Spatial-Temporal Multi-Cue (STMC) networks in an end-to-end SLT system with Transformer. ![]() This paper focuses on the translation system and improves performance by utilizing Transformer networks. Though SLT has gathered interest recently, little study has been performed on the translation system. Then, a translation system generates spoken language translations from the sign language glosses. Sign Language Translation (SLT) first uses a Sign Language Recognition (SLR) system to extract sign language glosses from videos.
0 Comments
Leave a Reply. |