Improvement in Sign Language Translation Using Text CTC Alignment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909439855951872 |
|---|---|
| author | Tan, Sihan Miyazaki, Taro Khan, Nabeela Nakadai, Kazuhiro |
| author_facet | Tan, Sihan Miyazaki, Taro Khan, Nabeela Nakadai, Kazuhiro |
| contents | Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language video and spoken text. In this work, we propose a novel method combining joint CTC/Attention and transfer learning. The joint CTC/Attention introduces hierarchical encoding and integrates CTC with the attention mechanism during decoding, effectively managing both monotonic and non-monotonic alignments. Meanwhile, transfer learning helps bridge the modality gap between vision and language in SLT. Experimental results on two widely adopted benchmarks, RWTH-PHOENIX-Weather 2014 T and CSL-Daily, show that our method achieves results comparable to state-of-the-art and outperforms the pure-attention baseline. Additionally, this work opens a new door for future research into gloss-free SLT using text-based CTC alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09014 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improvement in Sign Language Translation Using Text CTC Alignment Tan, Sihan Miyazaki, Taro Khan, Nabeela Nakadai, Kazuhiro Computation and Language Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language video and spoken text. In this work, we propose a novel method combining joint CTC/Attention and transfer learning. The joint CTC/Attention introduces hierarchical encoding and integrates CTC with the attention mechanism during decoding, effectively managing both monotonic and non-monotonic alignments. Meanwhile, transfer learning helps bridge the modality gap between vision and language in SLT. Experimental results on two widely adopted benchmarks, RWTH-PHOENIX-Weather 2014 T and CSL-Daily, show that our method achieves results comparable to state-of-the-art and outperforms the pure-attention baseline. Additionally, this work opens a new door for future research into gloss-free SLT using text-based CTC alignment. |
| title | Improvement in Sign Language Translation Using Text CTC Alignment |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.09014 |