DG-SED: Domain Generalization for Sound Event Detection with Heterogeneous Training Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908502622994432 |
|---|---|
| author | Xiao, Yang Yin, Han Bai, Jisheng Das, Rohan Kumar |
| author_facet | Xiao, Yang Yin, Han Bai, Jisheng Das, Rohan Kumar |
| contents | This work explores domain generalization (DG) for sound event detection (SED), advancing adaptability to real-world scenarios. Our approach employs a mean-teacher framework with domain generalization named DG-SED to integrate heterogeneous training data while preserving the SED model performance across the datasets. Specifically, we first apply mixstyle to the frequency dimension to adapt the mel-spectrograms from different domains. Next, we use the adaptive residual normalization method to generalize features across multiple domains by applying instance normalization in the frequency dimension. Lastly, we use the sound event bounding boxes method for post-processing. We evaluate the proposed approach DG-SED on the DCASE 2024 Challenge Task 4, measuring PSDS on the DESED dataset and macro-average pAUC on the MAESTRO dataset. The results indicate that the proposed DG-SED method improves both PSDS and macro-average pAUC compared to the baselines. The code will be released in due course. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03654 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DG-SED: Domain Generalization for Sound Event Detection with Heterogeneous Training Data Xiao, Yang Yin, Han Bai, Jisheng Das, Rohan Kumar Audio and Speech Processing This work explores domain generalization (DG) for sound event detection (SED), advancing adaptability to real-world scenarios. Our approach employs a mean-teacher framework with domain generalization named DG-SED to integrate heterogeneous training data while preserving the SED model performance across the datasets. Specifically, we first apply mixstyle to the frequency dimension to adapt the mel-spectrograms from different domains. Next, we use the adaptive residual normalization method to generalize features across multiple domains by applying instance normalization in the frequency dimension. Lastly, we use the sound event bounding boxes method for post-processing. We evaluate the proposed approach DG-SED on the DCASE 2024 Challenge Task 4, measuring PSDS on the DESED dataset and macro-average pAUC on the MAESTRO dataset. The results indicate that the proposed DG-SED method improves both PSDS and macro-average pAUC compared to the baselines. The code will be released in due course. |
| title | DG-SED: Domain Generalization for Sound Event Detection with Heterogeneous Training Data |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.03654 |