English
Related papers

Related papers: Multi-dimensional frequency dynamic convolution wi…

200 papers

Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-invariant dimension. To address this issue, dynamic…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-23 Haobo Yue , Zhicheng Zhang , Da Mu , Yonghao Dang , Jianqin Yin , Jin Tang

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…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-05 Hyeonuk Nam , Seong-Hu Kim , Byeong-Yun Ko , Yong-Hwa Park

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 shift invariance…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-17 Hyeonuk Nam

We explore on various attention methods on frequency and channel dimensions for sound event detection (SED) in order to enhance performance with minimal increase in computational cost while leveraging domain knowledge to address the…

Sound · Computer Science 2023-08-30 Hyeonuk Nam , Seong-Hu Kim , Deokki Min , Yong-Hwa Park

Frequency dynamic convolution (FDY conv) has been a milestone in the sound event detection (SED) field, but it involves a substantial increase in model size due to multiple basis kernels. In this work, we propose partial frequency dynamic…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-23 Hyeonuk Nam , Yong-Hwa Park

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…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-11 Hyeonuk Nam , Seong-Hu Kim , Deokki Min , Junhyeok Lee , Yong-Hwa Park

In this work, we conduct an in-depth analysis of two frequency-dependent methods for sound event detection (SED): FilterAugment and frequency dynamic convolution (FDY conv). The goal is to better understand their characteristics and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-28 Hyeonuk Nam , Seong-Hu Kim , Deokki Min , Byeong-Yun Ko , Yong-Hwa Park

Spatial convolution is fundamental in constructing deep Convolutional Neural Networks (CNNs) for visual recognition. While dynamic convolution enhances model accuracy by adaptively combining static kernels, it incurs significant…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Tianyu Zhang , Fan Wan , Haoran Duan , Kevin W. Tong , Jingjing Deng , Yang Long

In this paper, we propose a stacked convolutional and recurrent neural network (CRNN) with a 3D convolutional neural network (CNN) in the first layer for the multichannel sound event detection (SED) task. The 3D CNN enables the network to…

Sound · Computer Science 2018-01-30 Sharath Adavanne , Archontis Politis , Tuomas Virtanen

Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs). Instead, recent research in dynamic convolution shows that learning a linear…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Chao Li , Aojun Zhou , Anbang Yao

In sound event detection (SED), convolutional neural networks (CNNs) are widely employed to extract time-frequency (TF) patterns from spectrograms. However, the ability of CNNs to recognize different sound events is limited by their…

Sound · Computer Science 2024-10-30 Tao Song , WenWen Zhang

While Dynamic Convolution (DY-Conv) has shown promising performance by enabling adaptive weight selection through multiple parallel weights combined with an attention mechanism, the frequency response of these weights tends to exhibit high…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Linwei Chen , Lin Gu , Liang Li , Chenggang Yan , Ying Fu

Recent advances in deep learning, particularly frequency dynamic convolution (FDY conv), have significantly improved sound event detection (SED) by enabling frequency-adaptive feature extraction. However, FDY conv relies on temporal average…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-18 Hyeonuk Nam , Yong-Hwa Park

State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal…

While many deep learning methods on other domains have been applied to sound event detection (SED), differences between original domains of the methods and SED have not been appropriately considered so far. As SED uses audio data with two…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-24 Hyeonuk Nam , Seong-Hu Kim , Deokki Min , Byeong-Yun Ko , Seung-Deok Choi , Yong-Hwa Park

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)…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-13 Ji Won Kim , Sang Won Son , Yoonah Song , Hong Kook Kim , Il Hoon Song , Jeong Eun Lim

DNN-based methods have shown high performance in sound event localization and detection(SELD). While in real spatial sound scenes, reverberation and the imbalanced presence of various sound events increase the complexity of the SELD task.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-18 Siwei Huang , Jianfeng Chen , Jisheng Bai , Yafei Jia , Dongzhe Zhang

We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time…

Sound · Computer Science 2016-12-09 Naoya Takahashi , Michael Gygli , Beat Pfister , Luc Van Gool

This paper proposes to use low-level spatial features extracted from multichannel audio for sound event detection. We extend the convolutional recurrent neural network to handle more than one type of these multichannel features by learning…

Sound · Computer Science 2017-06-09 Sharath Adavanne , Pasi Pertilä , Tuomas Virtanen

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Jin Chen , Xijun Wang , Zichao Guo , Xiangyu Zhang , Jian Sun
‹ Prev 1 2 3 10 Next ›