Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914829932953600 |
|---|---|
| author | Nam, Hyeonuk Kim, Seong-Hu Min, Deokki Lee, Junhyeok Park, Yong-Hwa |
| author_facet | Nam, Hyeonuk Kim, Seong-Hu Min, Deokki Lee, Junhyeok Park, Yong-Hwa |
| contents | Frequency dynamic convolution (FDY conv) has shown the state-of-the-art performance in sound event detection (SED) using frequency-adaptive kernels obtained by frequency-varying combination of basis kernels. However, FDY conv lacks an explicit mean to diversify frequency-adaptive kernels, potentially limiting the performance. In addition, size of basis kernels is limited while time-frequency patterns span larger spectro-temporal range. Therefore, we propose dilated frequency dynamic convolution (DFD conv) which diversifies and expands frequency-adaptive kernels by introducing different dilation sizes to basis kernels. Experiments showed advantages of varying dilation sizes along frequency dimension, and analysis on attention weight variance proved dilated basis kernels are effectively diversified. By adapting class-wise median filter with intersection-based F1 score, proposed DFD-CRNN outperforms FDY-CRNN by 3.12% in terms of polyphonic sound detection score (PSDS). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05341 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection Nam, Hyeonuk Kim, Seong-Hu Min, Deokki Lee, Junhyeok Park, Yong-Hwa Audio and Speech Processing Sound Frequency dynamic convolution (FDY conv) has shown the state-of-the-art performance in sound event detection (SED) using frequency-adaptive kernels obtained by frequency-varying combination of basis kernels. However, FDY conv lacks an explicit mean to diversify frequency-adaptive kernels, potentially limiting the performance. In addition, size of basis kernels is limited while time-frequency patterns span larger spectro-temporal range. Therefore, we propose dilated frequency dynamic convolution (DFD conv) which diversifies and expands frequency-adaptive kernels by introducing different dilation sizes to basis kernels. Experiments showed advantages of varying dilation sizes along frequency dimension, and analysis on attention weight variance proved dilated basis kernels are effectively diversified. By adapting class-wise median filter with intersection-based F1 score, proposed DFD-CRNN outperforms FDY-CRNN by 3.12% in terms of polyphonic sound detection score (PSDS). |
| title | Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2406.05341 |