Leveraging Self-supervised Audio Representations for Data-Efficient Acoustic Scene Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917759795855360 |
|---|---|
| author | Cai, Yiqiang Li, Shengchen Shao, Xi |
| author_facet | Cai, Yiqiang Li, Shengchen Shao, Xi |
| contents | Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a powerful method for extracting features from unlabeled audio data, benefiting many downstream audio tasks. This paper proposes a data-efficient and low-complexity ASC system by leveraging self-supervised audio representations extracted from general-purpose audio datasets. We introduce BEATs, an audio SSL pre-trained model, to extract the general representations from AudioSet. Through extensive experiments, it has been demonstrated that the self-supervised audio representations can help to achieve high ASC accuracy with limited labeled fine-tuning data. Furthermore, we find that ensembling the SSL models fine-tuned with different strategies contributes to a further performance improvement. To meet low-complexity requirements, we use knowledge distillation to transfer the self-supervised knowledge from large teacher models to an efficient student model. The experimental results suggest that the self-supervised teachers effectively improve the classification accuracy of the student model. Our best-performing system obtains an average accuracy of 56.7%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14862 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Self-supervised Audio Representations for Data-Efficient Acoustic Scene Classification Cai, Yiqiang Li, Shengchen Shao, Xi Sound Audio and Speech Processing Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a powerful method for extracting features from unlabeled audio data, benefiting many downstream audio tasks. This paper proposes a data-efficient and low-complexity ASC system by leveraging self-supervised audio representations extracted from general-purpose audio datasets. We introduce BEATs, an audio SSL pre-trained model, to extract the general representations from AudioSet. Through extensive experiments, it has been demonstrated that the self-supervised audio representations can help to achieve high ASC accuracy with limited labeled fine-tuning data. Furthermore, we find that ensembling the SSL models fine-tuned with different strategies contributes to a further performance improvement. To meet low-complexity requirements, we use knowledge distillation to transfer the self-supervised knowledge from large teacher models to an efficient student model. The experimental results suggest that the self-supervised teachers effectively improve the classification accuracy of the student model. Our best-performing system obtains an average accuracy of 56.7%. |
| title | Leveraging Self-supervised Audio Representations for Data-Efficient Acoustic Scene Classification |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.14862 |