Streaming Audio Transformers for Online Audio Tagging
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911910928056320 |
|---|---|
| author | Dinkel, Heinrich Yan, Zhiyong Wang, Yongqing Zhang, Junbo Wang, Yujun Wang, Bin |
| author_facet | Dinkel, Heinrich Yan, Zhiyong Wang, Yongqing Zhang, Junbo Wang, Yujun Wang, Bin |
| contents | Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory usage, slow inference speed, and considerable model delay, rendering them impractical for real-world AT applications. In this study, we introduce streaming audio transformers (SAT) that combine the vision transformer (ViT) architecture with Transformer-Xl-like chunk processing, enabling efficient processing of long-range audio signals. Our proposed SAT is benchmarked against other transformer-based SOTA methods, achieving significant improvements in terms of mean average precision (mAP) at a delay of 2s and 1s, while also exhibiting significantly lower memory usage and computational overhead. Checkpoints are publicly available https://github.com/RicherMans/SAT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_17834 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Streaming Audio Transformers for Online Audio Tagging Dinkel, Heinrich Yan, Zhiyong Wang, Yongqing Zhang, Junbo Wang, Yujun Wang, Bin Sound Audio and Speech Processing Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory usage, slow inference speed, and considerable model delay, rendering them impractical for real-world AT applications. In this study, we introduce streaming audio transformers (SAT) that combine the vision transformer (ViT) architecture with Transformer-Xl-like chunk processing, enabling efficient processing of long-range audio signals. Our proposed SAT is benchmarked against other transformer-based SOTA methods, achieving significant improvements in terms of mean average precision (mAP) at a delay of 2s and 1s, while also exhibiting significantly lower memory usage and computational overhead. Checkpoints are publicly available https://github.com/RicherMans/SAT. |
| title | Streaming Audio Transformers for Online Audio Tagging |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2305.17834 |