Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.20036 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916866814902272 |
|---|---|
| author | Taylor, James Mack, Wolfgang |
| author_facet | Taylor, James Mack, Wolfgang |
| contents | State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks trained through contrastive learning to align audio and text representations. Identifying the optimal text description for an audio class is challenging, particularly when the class comprises a wide variety of sounds. This paper examines few-shot methods designed to improve classification accuracy beyond the zero-shot approach. Specifically, audio embeddings are grouped by class and processed to replace the inherently noisy text embeddings. Our results demonstrate that few-shot classification typically outperforms the zero-shot baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20036 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Audio Classification by Transitioning from Zero- to Few-Shot Taylor, James Mack, Wolfgang Sound Machine Learning State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks trained through contrastive learning to align audio and text representations. Identifying the optimal text description for an audio class is challenging, particularly when the class comprises a wide variety of sounds. This paper examines few-shot methods designed to improve classification accuracy beyond the zero-shot approach. Specifically, audio embeddings are grouped by class and processed to replace the inherently noisy text embeddings. Our results demonstrate that few-shot classification typically outperforms the zero-shot baseline. |
| title | Improving Audio Classification by Transitioning from Zero- to Few-Shot |
| topic | Sound Machine Learning |
| url | https://arxiv.org/abs/2507.20036 |