Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection

doi:doi:10.57702/he0quqgp

Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection

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.

BibTex:

@dataset{Hyeonuk_Nam_and_Seong-Hu_Kim_and_Deokki_Min_and_Junhyeok_Lee_and_Yong-Hwa_Park_2024,
    abstract = {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.},
    author = {Hyeonuk Nam and Seong-Hu Kim and Deokki Min and Junhyeok Lee and Yong-Hwa Park},
    doi = {10.57702/he0quqgp},
    institution = {No Organization},
    keyword = {'Dilated Convolution', 'Frequency-Adaptive Convolution', 'Sound Event Detection'},
    month = {dec},
    publisher = {TIB},
    title = {Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection},
    url = {https://service.tib.eu/ldmservice/dataset/diversifying-and-expanding-frequency-adaptive-convolution-kernels-for-sound-event-detection},
    year = {2024}
}