检索结果-内蒙古大学图书馆

Semi-supervised sound event detection with dynamic convolution and confidence-aware mean teacher

DIGITAL SIGNAL PROCESSING 2025年 156卷

作者： Xiao, Shengchang Zhang, Xueshuai Zhang, Pengyuan Yan, Yonghong Chinese Acad Sci Inst Acoust Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Recently, sound event detection (SED) has made significant advancements through the application of deep learning, but there are still many difficulties and challenges to be addressed. One of the major challenges is the diversity of sound events, leading to substantial variations in time-frequency domain features. Additionally, most existing SED models can not effectively handle sound events of different scales, particularly those of short duration. Another challenge is the lack of well labeled dataset. The commonly used solution is mean teacher method, but inaccurate pseudo-labels could lead to confirmation bias and performance imbalance. In this paper, we introduce the multi-dimensional frequency dynamic convolution, which endows convolutional kernels with frequency-adaptive dynamic properties to enhance the feature representation capability. Moreover, we propose dual self attention pooling function to achieve more precise temporal localization. Finally, to solve the incorrect pseudo-labels problems, we propose the confidence-aware mean teacher to increase pseudo-labels accuracy and train the student model with high confidence labels. Experimental results on DCASE2017, DCASE2018 and DCASE2023 Task4 dataset validate the superior performance of proposed methods.

关键词： sound event detection Dynamic convolution Mean teacher Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Edge computing for driving safety: evaluating deep learning models for cost-effective sound event detection

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-15页

作者： Castorena, Carlos Lopez-Ballester, Jesus De Rus, Juan A. Cobos, Maximo Ferri, Francesc J. Univ Valencia Comp Sci Dept Burjassot Spain

This paper addresses road safety concerns by investigating low-cost solutions for sound event detection (SED) tailored to driving scenarios. While advanced technologies like deep learning hold promise for improving road safety, their practical implementation often involves expensive sensors and hardware. Distractions, a major cause of accidents, require effective detection and mitigation. This study concentrates on auditory distractions and utilizes SED with low-cost edge devices to identify and timestamp relevant audio events, providing valuable insights into the driving environment. We evaluate state-of-the-art deep learning models on various edge devices, including the 2023 DCASE baseline with convolutional recurrent neural networks (CRNN) and an adapted YOLO vision model for audio spectrograms. Our analysis spans different hardware options, including single-board computers (SBCs) and desktop equipment, offering guidance on cost-effective hardware selection for in-vehicle SED applications. This research aims to contribute to affordable SED solutions in the context of driving safety, with the ultimate goal of advancing road safety efforts worldwide.

关键词： sound event detection Deep learning Driver safety Smart vehicles Edge computing platforms

来源：评论

学校读者我要写书评

暂无评论

MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous sound event detection

MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregat...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Zehao Yue, Haobo Zhang, Zhicheng Mu, Da Tang, Jin Yin, Jianqin School of Artificial Intelligence Beijing University of Posts and Telecommunications China School of Intelligent Engineering and Automation Beijing University of Posts and Telecommunications China

ISBN: (纸本)9798350368741

sound event detection (SED) plays a vital role in comprehending and perceiving acoustic scenes. Previous methods have demonstrated impressive capabilities. However, they are deficient in learning features of complex scenes from heterogeneous dataset. In this paper, we introduce a novel dual-branch architecture named Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous sound event detection (MTDA-HSED). The MTDA-HSED architecture employs the Mutual-Assistance Audio Adapter (M3A) to effectively tackle the multi-scenario problem and uses the Dual-Branch Mid-Fusion (DBMF) module to tackle the multi-granularity problem. Specifically, M3A is integrated into the BEATs block as an adapter to improve the BEATs' performance by fine-tuning it on the multi-scenario dataset. The DBMF module connects BEATs and CNN branches, which facilitates the deep fusion of information from the BEATs and the CNN branches. Experimental results show that the proposed methods exceed the baseline of mpAUC by 5% on the DESED and MAESTRO Real datasets. © 2025 IEEE.

关键词： adapter aggregate sound event detection

来源：评论

学校读者我要写书评

暂无评论

Frequency-Aware Convolution for sound event detection 31st

Frequency-Aware Convolution for Sound Event Detection

引用

31st International Conference on Multimedia Modeling

作者： Song, Tao Zhang, Wenwen Kuaishou Technol Beijing Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9789819620531;9789819620548

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 insensitivity to shifts of TF patterns along the frequency dimension, caused by translation equivariance. To address this issue, a model called frequency dynamic convolution (FDY) has been proposed, which involves applying specific convolution kernels to different frequency components. However, FDY requires a significantly larger number of parameters and computational resources compared to a standard CNN. This paper proposes a more efficient solution called frequency-aware convolution (FAC). FAC incorporates frequency positional information by encoding it in a vector, which is then explicitly added to the input spectrogram. To ensure that the amplitude of the encoding vector matches that of the input spectrogram, the encoding vector is adaptively and channel-dependently scaled using self-attention. To evaluate the effectiveness of FAC, we conducted experiments within the context of the DCASE 2023 task 4. The results show that FAC achieves comparable performance to FDY while requiring only an additional 515 parameters, whereas FDY necessitates an additional 8.02 million parameters. Furthermore, an ablation study confirms that the adaptive and channel-dependent scaling of the encoding vector is critical to the performance of FAC.

关键词： sound event detection CNN Frequency-aware convolution

来源：评论

学校读者我要写书评

暂无评论

UCIL: An Unsupervised Class Incremental Learning Approach for sound event detection

UCIL: An Unsupervised Class Incremental Learning Approach fo...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xiao, Yang Das, Rohan Kumar Fortemedia Singapore Singapore

ISBN: (纸本)9798350368741

This work explores class-incremental learning (CIL) for sound event detection (SED), advancing adaptability towards real-world scenarios. CIL's success in domains like computer vision inspired our SED-tailored method, addressing the unique challenges of diverse and complex audio environments. Our approach employs an independent unsupervised learning framework with a distillation loss function to integrate new sound classes while preserving the SED model consistency across incremental tasks. We further enhance this framework with a sample selection strategy for unlabeled data and a balanced exemplar update mechanism, ensuring varied and illustrative sound representations. Evaluating various continual learning methods on the DCASE 2023 Task 4 dataset, our research offers insights into each method's applicability for real-world SED systems that can have newly added sound classes. The findings also delineate future directions of CIL in dynamic audio settings. © 2025 IEEE.

关键词： continual learning sound event detection

来源：评论

学校读者我要写书评

暂无评论

Prototype based Masked Audio Model for Self-Supervised Learning of sound event detection

Prototype based Masked Audio Model for Self-Supervised Learn...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Cai, Pengfei Song, Yan Jiang, Nan Gu, Qing McLoughlin, Ian National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China China ICT Cluster Singapore Institute of Technology Singapore

ISBN: (纸本)9798350368741

A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn from unlabeled data, and the performance is constrained by the quality and size of the former. In this paper, we introduce the Prototype based Masked Audio Model (PMAM) algorithm for self-supervised representation learning in SED, to better exploit unlabeled data. Specifically, semantically rich frame-level pseudo labels are constructed from a Gaussian mixture model (GMM) based prototypical distribution modeling. These pseudo labels supervise the leaning of a Transformer-based masked audio model, in which binary cross-entropy loss is employed instead of the widely used InfoNCE loss, to provide independent loss contributions from different prototypes, which is important in real scenarios in which multiple labels may apply to unsupervised data frames. A final stage of fine-tuning with just a small amount of labeled data yields a very high performing SED model. On like-for-like tests using the DESED task, our method achieves a PSDS1 score of 62.5%, surpassing current state-of-the-art models and demonstrating the superiority of the proposed technique. © 2025 IEEE.

关键词： masked audio model prototype self-supervised learning sound event detection

来源：评论

学校读者我要写书评

暂无评论

Formula-Supervised sound event detection: Pre-Training Without Real Data

Formula-Supervised Sound Event Detection: Pre-Training Witho...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shibata, Yuto Tanaka, Keitaro Bando, Yoshiaki Imoto, Keisuke Kataoka, Hirokatsu Aoki, Yoshimitsu Keio University Japan Japan Waseda University Japan Doshisha University Japan University of Oxford United Kingdom

ISBN: (纸本)9798350368741

In this paper, we propose a novel formula-driven supervised learning (FDSL) framework for pre-training an environmental sound analysis model by leveraging acoustic signals parametrically synthesized through formula-driven methods. Specifically, we outline detailed procedures and evaluate their effectiveness for sound event detection (SED). The SED task, which involves estimating the types and timings of sound events, is particularly challenged by the difficulty of acquiring a sufficient quantity of accurately labeled training data. Moreover, it is well known that manually annotated labels often contain noises and are significantly influenced by the subjective judgment of annotators. To address these challenges, we propose a novel pre-training method that utilizes a synthetic dataset, Formula-SED, where acoustic data are generated solely based on mathematical formulas. The proposed method enables large-scale pre-training by using the synthesis parameters applied at each time step as ground truth labels, thereby eliminating label noise and bias. We demonstrate that large-scale pre-training with Formula-SED significantly enhances model accuracy and accelerates training, as evidenced by our results in the DESED dataset used for DCASE2023 Challenge Task 4. The project page is at https://***/Formula-SED/. © 2025 IEEE.

关键词： environmental sound synthesis pre-training without real data sound event detection

来源：评论

学校读者我要写书评

暂无评论

Debiased Training For Semi-supervised sound event detection

Debiased Training For Semi-supervised Sound Event Detection

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xiao, Shengchang Zhang, Xueshuai Zhang, Pengyuan Yan, Yonghong Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics Chinese Academy of Sciences University of Chinese Academy of Sciences China

ISBN: (纸本)9798350368741

Recently, semi-supervised sound event detection has attracted increasing research interest due to the scarcity of labeled data. However, traditional semi-supervised learning methods can lead to training instability and confirmation bias because of potentially incorrect pseudo labels. To address this issue, we propose the debiased training, a novel approach to reduce the inherent bias of pseudo labels. Debiased training can effectively decouple the generation and utilization of pseudo labels to mitigate the error accumulation and promote model's robustness against biased pseudo labels. In addition, we introduce the channel restruction module (CRM) to decrease redundant computing and facilitate representation ability. Experimental results on DCASE 2023 task4 dataset show that the proposed methods significantly enhance the performance of semi-supervised methods while maintaining relatively low computational complexity. © 2025 IEEE.

关键词： Mean teacher sound event detection

来源：评论

学校读者我要写书评

暂无评论

ASiT-CRNN: A method for sound event detection with fine-tuning of self-supervised pre-trained ASiT-based model

引用

DIGITAL SIGNAL PROCESSING 2025年 160卷

作者： Zheng, Yueyang Zhang, Ruikun Atito, Sara Yang, Shuguo Wang, Wenwu Mei, Yiduo Qingdao Univ Sci & Technol Sch Math & Phys Qingdao Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc CVSSP Ctr Vis Speech & Signal Proc CVSSP Guildford England Inspur Yunzhou Ind Internet Co Ltd Jinan Peoples R China

Recently, the utilization of pre-trained models to transfer knowledge to downstream tasks has become an increasing trend. In this paper, we present an effective sound event detection (SED) method, which improves the performance of a baseline system based on convolutional recurrent neural network (CRNN) for the DCASE 2022 Task 4 by embedding a local-global audio spectrogram vision transformer (ASiT) with a two-phase finetuning strategy, thus referred to as ASiT-CRNN. ASiT is based on the audio classification task and is a pre-trained model on the large-scale audio dataset AudioSet using several self-supervised learning (SSL) methods. However, due to the differences between the clip-level and frame-level tasks, inputting the output of ASiT into the SED task without any processing does not give the desired results. Therefore, the ASiT-CRNN model adopts frequency- averaged pooling (FAP) and nearest neighbour interpolation (NNI) operations on the ASiT output based on the original network architecture, aiming at obtaining a sequence of frame-level features and improving the temporal resolution of the embedding. Two complementary feature sequences, ASiT and CNN, are also fused to obtain a higher quality and more discriminative representation of audio features. We train the ASiT-CRNN model on the development set of DCASE 2022 Task 4 and fine-tune it in two phases using semi-supervised mean-teacher methods to address the challenges of limited labelled data. Finally, we also fairly compare ASiT with several other self-supervised pre-trained models on the SED task. The ASiT-CRNN model achieves PSDS1 and PSDS2 scores of 0.488 and 0.767, respectively, performing significantly better than those of the baseline system, CRNN, of 0.351 and 0.552. In addition, ASiT-CRNN outperforms several other SSL pre-trained models based on SED tasks in the comparison experiments. Open source code at https://***/qingkezyy/ASiT-CRNN.

关键词： sound event detection Self-supervised pre-trained model Vision transformer Feature fusion Fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Multi-granularity acoustic information fusion for sound event detection

引用

SIGNAL PROCESSING 2025年 227卷

作者： Yin, Han Chen, Jianfeng Bai, Jisheng Wang, Mou Rahardja, Susanto Shi, Dongyuan Gan, Woon-seng Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China Chinese Acad Sci Inst Acoust Beijing 100190 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

Most previous works on sound event detection (SED) are based on binary hard labels of sound events, leaving other scales of information underexplored. To address this problem, we introduce multiple granularities of knowledge into the system to perform hierarchical acoustic information fusion for SED. Specifically, we present an interactive dual-conformer (IDC) module to adaptively fuse the medium-grained and fine-grained acoustic information based on the hard and soft labels of sound events. In addition, we propose a scene-dependent mask estimator (SDME) module to extract the coarse-grained information from acoustic scenes, introducing the scene-event relationships into the SED system. Experimental results show that the proposed IDC and SDME modules efficiently fuse the acoustic information at different scales and therefore further improve the SED performance. The proposed system achieved Top 1 performance in DCASE 2023 Challenge Task 4B.

关键词： sound event detection Multi-granularity acoustic information Soft labels Hard labels Scene-event relationships

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：