Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection
2D convolution is widely used in sound event detection (SED) to recognize two dimensional time-frequency patterns of sound events. However, 2D convolution enforces translation equivariance on sound events along both time and frequency axis while frequency is not shift-invariant dimension. In order to improve physical consistency of 2D convolution on SED, we propose frequency dynamic convolution which applies kernel that adapts to frequency components of input. Frequency dynamic convolution outperforms the baseline by 6.3% in DESED validation dataset in terms of polyphonic sound detection score (PSDS). It also significantly outperforms other pre-existing content-adaptive methods on SED. In addition, by comparing class-wise F1 scores of baseline and frequency dynamic convolution, we showed that frequency dynamic convolution is especially more effective for detection of non-stationary sound events with intricate time-frequency patterns. From this result, we verified that frequency dynamic convolution is superior in recognizing frequency-dependent patterns.
Code (1)
Tasks
Event DetectionSound Event DetectionTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
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…
Event DetectionSound Event DetectionFrequency Dynamic Convolutions for Sound Event Detection
Recent research in deep learning-based Sound Event Detection (SED) has primarily focused on Convolutional Recurrent Neural Networks (CRNNs) and Transformer models. However, conventional 2D convolution-based models assume…
ARCEvent DetectionSound Event DetectionTowards Understanding of Frequency Dependence on Sound Event Detection
In this work, various analysis methods are conducted on frequency-dependent methods on SED to further delve into their detailed characteristics and behaviors on SED. While SED has been rapidly advancing through the adopt…
Data AugmentationEvent DetectionSound Event DetectionFrequency-Adaptive Dilated Convolution for Semantic Segmentation
Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision. In this study, we propose three strategies to improve individual phases of…
object-detectionObject DetectionSemantic SegmentationMulti-dimensional frequency dynamic convolution with confident mean teacher for sound event detection
Recently, convolutional neural networks (CNNs) have been widely used in sound event detection (SED). However, traditional convolution is deficient in learning time-frequency domain representation of different sound event…
Event DetectionSound Event Detection