Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.07919 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929460171767808 |
|---|---|
| author | Li, Yiming Guo, Zhifang Wang, Xiangdong Liu, Hong |
| author_facet | Li, Yiming Guo, Zhifang Wang, Xiangdong Liu, Hong |
| contents | Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks. These models usually aggregate uni-modal local representations, namely frame or word features, into global ones, on which the contrastive loss is employed to reach coarse-grained cross-modal alignment. However, frame-level correspondence with texts may be ignored, making it ill-posed on explainability and fine-grained challenges which may also undermine performances on coarse-grained tasks. In this work, we aim to improve both coarse- and fine-grained audio-language alignment in large-scale contrastive pre-training. To unify the granularity and latent distribution of two modalities, a shared codebook is adopted to represent multi-modal global features with common bases, and each codeword is regularized to encode modality-shared semantics, bridging the gap between frame and word features. Based on it, a locality-aware block is involved to purify local patterns, and a hard-negative guided loss is devised to boost alignment. Experiments on eleven zero-shot coarse- and fine-grained tasks suggest that our model not only surpasses the baseline CLAP significantly but also yields superior or competitive results compared to current SOTA works. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07919 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training Li, Yiming Guo, Zhifang Wang, Xiangdong Liu, Hong Audio and Speech Processing Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks. These models usually aggregate uni-modal local representations, namely frame or word features, into global ones, on which the contrastive loss is employed to reach coarse-grained cross-modal alignment. However, frame-level correspondence with texts may be ignored, making it ill-posed on explainability and fine-grained challenges which may also undermine performances on coarse-grained tasks. In this work, we aim to improve both coarse- and fine-grained audio-language alignment in large-scale contrastive pre-training. To unify the granularity and latent distribution of two modalities, a shared codebook is adopted to represent multi-modal global features with common bases, and each codeword is regularized to encode modality-shared semantics, bridging the gap between frame and word features. Based on it, a locality-aware block is involved to purify local patterns, and a hard-negative guided loss is devised to boost alignment. Experiments on eleven zero-shot coarse- and fine-grained tasks suggest that our model not only surpasses the baseline CLAP significantly but also yields superior or competitive results compared to current SOTA works. |
| title | Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.07919 |