2010年3月7日 · Non-stationary sound events such as alarm/bell ringing, cat, dishes, dog, electric shaver/toothbrush, running water and speech exhibits intricate time-frequency patterns (example shown below (b), a log mel spectrogram of speech sound).

2024年6月8日 · 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.

2022年3月29日 · 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.

2023年6月10日 · This report proposes a frequency dynamic convolution (FDY) with a large kernel attention (LKA)-convolutional recurrent neural network (CRNN) with a pre-trained bidirectional encoder representation from audio transformers (BEATs) embedding-based sound event detection (SED) model that employs a mean-teacher and pseudo-label approach to address the...

2024年3月2日 · 基于基线模型和fdy-crnn的分类性能比较，可以更详细地分析频率动态卷积如何影响声音事件检测（sed）性能。 我们选择了以下性能代表模型进行比较：基线模型的PSDS1为0.412，PSDS2为0.634，CB-F1为0.515，FDY-CRNN的PSDS1为0.432，PSDS2为0.643，CB-F1 …

Frequency dynamic convolution (FDY conv) has shown the state-of-the-art performance in sound event detection (SED) us-ing frequency-adaptive kernels obtained by frequency-varying combination of basis kernels. However, FDY conv lacks an explicit mean to diversify frequency-adaptive kernels, poten-tially limiting the performance.

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.

Frequency Dynamic Convolution-Recurrent Neural Network (FDY-CRNN) for Sound Event Detection \n \n. Official implementation of \n \n; Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection (Accepted to INTERSPEECH 2022) \nby Hyeonuk Nam, Seong-Hu Kim, Byeong-Yun Ko, Yong-Hwa Park \n \n Frequency Dynamic ...

2010年3月7日 · Multi-Dilated Frequency Dynamic Convolution for Sound Event Detection Includes following methods: Dilated Frequency Dynamic Convolution, Partial Frequency Dynamic Convolution, Partial Dilated Frequency Dynamic Convolution and Multi-Dilated Frequency Dynamic Convolution

频率动态卷积（FDY conv）一直是声音事件检测（SED）领域的里程碑，但由于多个基础内核，它导致模型大小大幅增加。 在这项工作中，我们提出了部分频率动态卷积（PFD conv），它将静态传统2D卷积分 支输出和动态FDY conv分支输出连接起来，以便在保持性能的同时 ...