Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909525469036544 |
|---|---|
| author | He, Yi Yang, Lei Wang, Shilin |
| author_facet | He, Yi Yang, Lei Wang, Shilin |
| contents | This paper introduces a novel approach to Visual Forced Alignment (VFA), aiming to accurately synchronize utterances with corresponding lip movements, without relying on audio cues. We propose a novel VFA approach that integrates a local context-aware feature extractor and employs multi-task learning to refine both global and local context features, enhancing sensitivity to subtle lip movements for precise word-level and phoneme-level alignment. Incorporating the improved Viterbi algorithm for post-processing, our method significantly reduces misalignments. Experimental results show our approach outperforms existing methods, achieving a 6% accuracy improvement at the word-level and 27% improvement at the phoneme-level in LRS2 dataset. These improvements offer new potential for applications in automatically subtitling TV shows or user-generated content platforms like TikTok and YouTube Shorts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning He, Yi Yang, Lei Wang, Shilin Computer Vision and Pattern Recognition This paper introduces a novel approach to Visual Forced Alignment (VFA), aiming to accurately synchronize utterances with corresponding lip movements, without relying on audio cues. We propose a novel VFA approach that integrates a local context-aware feature extractor and employs multi-task learning to refine both global and local context features, enhancing sensitivity to subtle lip movements for precise word-level and phoneme-level alignment. Incorporating the improved Viterbi algorithm for post-processing, our method significantly reduces misalignments. Experimental results show our approach outperforms existing methods, achieving a 6% accuracy improvement at the word-level and 27% improvement at the phoneme-level in LRS2 dataset. These improvements offer new potential for applications in automatically subtitling TV shows or user-generated content platforms like TikTok and YouTube Shorts. |
| title | Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.03286 |