UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909454218297344 |
|---|---|
| author | Xiao, Yang Das, Rohan Kumar |
| author_facet | Xiao, Yang Das, Rohan Kumar |
| contents | This work explores class-incremental learning (CIL) for sound event detection (SED), advancing adaptability towards real-world scenarios. CIL's success in domains like computer vision inspired our SED-tailored method, addressing the unique challenges of diverse and complex audio environments. Our approach employs an independent unsupervised learning framework with a distillation loss function to integrate new sound classes while preserving the SED model consistency across incremental tasks. We further enhance this framework with a sample selection strategy for unlabeled data and a balanced exemplar update mechanism, ensuring varied and illustrative sound representations. Evaluating various continual learning methods on the DCASE 2023 Task 4 dataset, we find that our research offers insights into each method's applicability for real-world SED systems that can have newly added sound classes. The findings also delineate future directions of CIL in dynamic audio settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03657 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detection Xiao, Yang Das, Rohan Kumar Audio and Speech Processing Sound This work explores class-incremental learning (CIL) for sound event detection (SED), advancing adaptability towards real-world scenarios. CIL's success in domains like computer vision inspired our SED-tailored method, addressing the unique challenges of diverse and complex audio environments. Our approach employs an independent unsupervised learning framework with a distillation loss function to integrate new sound classes while preserving the SED model consistency across incremental tasks. We further enhance this framework with a sample selection strategy for unlabeled data and a balanced exemplar update mechanism, ensuring varied and illustrative sound representations. Evaluating various continual learning methods on the DCASE 2023 Task 4 dataset, we find that our research offers insights into each method's applicability for real-world SED systems that can have newly added sound classes. The findings also delineate future directions of CIL in dynamic audio settings. |
| title | UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detection |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2407.03657 |