@techreport{Chen2025,
    Author = "Chen, Xuanyan and Xie, Wei",
    title = "McCi Submission to {DCASE} 2025: Training Low-Complexity Acoustic Scene Classification System with Knowledge Distillation and Curriculum",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "The Task 1 of DCASE 2025 focuses on different aspects of Acoustic Scene Classification(ASC) including recording device mismatch, low complexity constraints, data efficiency and the development of recording-device-specific models. This technical report describes the system we submitted. We first trained several teacher models on the ASC dataset through Self-Distillation and Curriculum Learning techniques.These teacher models included a model pre-trained on the AudioSet. Then we distill the knowledge from the teacher model into the student model via curriculum learning. We used the same inference model (i.e., student model) and data augmentation settings as provided in the baseline system. In experiments, our best system achieved an accuracy of 57.66\%."
}

@techreport{Gurugubelli2025,
    Author = "Gurugubelli, Krishna and Solanki, Ravi and Viswanathan, Sujith and Rayappa Kamble, Madhu and Deo, Aditi and Udupa, Abhinandan and Viswanathan, Ramya and K S, Rajesh Krishna",
    title = "Srib Submission for {DCASE} 2025 Challenge Task-1: Low-Complexity Acoustic Scene Classification with Device Information",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "This report details our submission for Task 1: Low-Complexity Acoustic Scene Classification with Device Information in the DCASE2025 challenge[1]. Our method builds upon the leading system from the DCASE2023 competition. Specifically, we have explored the CP-Mobile architecture in this work. To improve the generalization across devices, we incorporate several data augmentation strategies, including Freq-Mix-Style, frequency masking, and time rolling. To meet the model complexity requirements of the competition, we have evaluated the model with 16-bit precision. Hence, we have incorporated the mixed precision training to achieve the better performance during inference with 16-bit model. Our results show significant improvements in test accuracy over the baseline, confirming the effectiveness of our approach across all subsets."
}

@techreport{Han2025,
    Author = "Han, Seung-Gyu and Byun, Pil Moo and Chang, Joon-Hyuk",
    title = "Hyu Submission for {DCASE} 2025 Task 1: Low-Complexity Acoustic Scene Classification Using Reparameterizable {CNN} with Channel-Time-Frequency Attention",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "This paper presents the Hanyang University team’s submission for the DCASE 2025 Challenge Task 1: Low-Complexity Acoustic Scene Classification with Device Information. The task focuses on developing compact and efficient models that generalize well across both seen and unseen recording devices, under strict constraints on model size and computational cost. To address these challenges, we propose Rep-CTFA, a lightweight convolutional neural network that integrates two key design elements: (1) reparameterizable convolutional blocks with learnable branch scaling coefficients, and (2) a Channel-Time-Frequency Attention (CTFA) module. In addition, we explore input resolution variation by adjusting the hop length and number of mel bins to control time-frequency granularity. Knowledge distillation from a PaSST-based teacher ensemble is used to guide the training of the student model, improving generalization. Finally, we adopt a device-aware fine-tuning scheme that updates lightweight classification heads per device while keeping the shared backbone intact."
}

@techreport{Han2025a,
    Author = "Han, Sarang and Lee, Dong Ho and Jo, Min Sik and Ha, Eun Seo and Chae, Min Ju and Lee, Geon Woo",
    title = "Confidence-Aware Ensemble Knowledge Distillation for Low-Complexity Acoustic Scene Classification",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "We propose a confidence-aware ensemble knowledge distillation method for acoustic scene classification under low-complexity and limited-data settings. Our approach utilizes heterogeneous teacher models—BEATs, and EfficientAT—fine-tuned on the DCASE 2025 Task 1 dataset, to guide the training of a lightweight student model, TFSepNet. To improve over naive ensemble distillation, we introduce a confidence-weighted strategy that emphasizes reliable teacher outputs. Experimental results show improved generalization on unseen devices and domains, outperforming single-teacher and uniform ensemble baselines."
}

@techreport{Jeong2025,
    Author = "Jeong, Seunggyu and Kim, Seongeon",
    title = "Adaptive Knowledge Distillation Using a Device-Aware Teacher for Low-Complexity Acoustic Scene Classification",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "In this technical report, we describe our submission for Task 1, Low-Complexity Device-Robust Acoustic Scene Classification, of the DCASE 2025 Challenge. Our work tackles the dual challenges of strict complexity constraints and robust generalization to both seen and unseen devices, while also leveraging the new rule allowing the use of device labels at test time. Our proposed system is based on a knowledge distillation framework where an efficient CP-MobileNet student learns from a compact, specialized two-teacher ensemble. This ensemble combines a baseline PaSST teacher, trained with standard cross-entropy, and a ’generalization expert’ teacher. This expert is trained using our novel Device-Aware Feature Alignment (DAFA) loss, adapted from prior work, which explicitly structures the feature space for device robustness. To capitalize on the availability of test-time device labels, the distilled student model then undergoes a final device-specific fine-tuning stage. Our proposed system achieves a final accuracy of 57.93\% on the development set, demonstrating a significant improvement over the official baseline, particularly on unseen devices."
}

@techreport{Karasin2025,
    Author = "Karasin, Dominik and Olariu, Ioan-Cristian and Schöpf, Michael and Szymańska, Anna",
    title = "Domain-Specific External Data Pre-Training and Device-Aware Distillation for Data-Efficient Acoustic Scene Classification",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "In this technical report, we present our submission to the DCASE 2025 Challenge Task 1: Low-Complexity Acoustic Scene Classification with Device Information. Our approach centers on a compact CP-Mobile student model distilled via Bayesian ensemble averaging from different combinations of three teacher architectures: CP-ResNet, BEATs, and PaSST—using AudioSet pretrained check-points for the last two. We then fine-tune the student on each recording device to improve per-device classification accuracy. To compensate for the limited 25\% train-split, we pre-train both teacher and student on CochlScene and apply data augmentation, of which Device Impulse Response augmentation was particularly effective."
}

@techreport{Li2025,
    Author = "Li, Haowen and Yang, Ziyi and Wang, Mou and Tan, Ee-Leng and Yeow, Junwei and Peksi, Santi and Gan, Woon-Seng",
    title = "Joint Feature and Output Distillation for Low-Complexity Acoustic Scene Classification",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "This report presents a dual-level knowledge distillation framework with multi-teacher guidance for low-complexity acoustic scene classification (ASC) in DCASE2025 Task 1. We propose a distillation strategy that jointly transfers both soft logits and intermediate feature representations. Specifically, we pre-trained PaSST and CP-ResNet models as teacher models. Logits from teachers are averaged to generate soft targets, while one CP-ResNet is selected for feature-level distillation. This enables the compact student model (CP-Mobile) to capture both semantic distribution and structural information from teacher guidance. Experiments on the TAU Urban Acoustic Scenes 2022 Mobile dataset (development set) demonstrate that our submitted systems achieve up to 59.30\% accuracy."
}

@techreport{Luo2025,
    Author = "Luo, Yuandong and Liu, Hongqing and Shi, Liming and Gan, Lu",
    title = "Dynacp: Dynamic Parallel Selective Convolution in Cp-Mobile Under Multi-Teacher Distillation for Acoustic Scene Classification",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "This report introduces the acoustic scene classification (ASC) architecture submitted by the Chongqing University of Posts and Telecommunications – Audio Lab (CQUPT-AUL) for DCASE 2025 Task 1. The architecture is a lightweight and efficient network structure, termed as DynaCP. Built upon CP-Mobile, DynaCP dynamically selects between dilated convolutions with pooling or depth-wise convolutions with pooling at different network layers, thereby enhancing multi-scale feature representation with minimal computational overhead, while also alleviating the issue of information sparsity caused by dilated convolutions. To improve classification accuracy, a multi-teacher knowledge distillation approach is employed using pre-trained models of DYMN and MN. Experimental results demonstrate that DynaCP achieves competitive performance while maintaining low computational complexity."
}

@techreport{Ramezanee2025,
    Author = "Ramezanee, Mohamad Mahdee and Sharify, Hossein and Mehrani Kia, Amir Mohamad and Raoufi, Behnam",
    title = "Acoustic Scene Classification with Knowledge Distillation and Device-Specific Fine-Tuning for {DCASE} 2025",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "The objective of the acoustic scene classification task is to categorize audio recordings into one of ten predetermined environmental sound categories, such as urban parks or metro stations. This report to Task 1 of the DCASE 2025 Challenge, which emphasizes developing data-efficient, low-complexity systems for acoustic scene classification, addressing real-world constraints like limited training data and device mismatches [1]. Our model is designed with a reparameterizable convolutional structure that unifies multiple asymmetric kernels into a single efficient layer during inference, enabling both rich spatial representation and computational efficiency. It further integrates a novel attention-guided pooling strategy and a hybrid normalization scheme to enhance feature discrimination and stability throughout the network. Finally, we utilized ensemble learning of the newly defined teacher models and minimized the KL divergence between the student and teacher models to improve the results."
}

@techreport{Tan2025,
    Author = "Tan, Ee-Leng and Yeow, Jun Wei and Peksi, Santi and Li, Haowen and Yang, Ziyi and Gan, Woon-Seng",
    title = "SNTL-Ntu Dcase25 Submission: Acoustic Scene Classification Using {CNN}-{GRU} Model Without Knowledge Distillation",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "In this technical report, we present the SNTL-NTU team’s Task 1 submission for the Low-Complexity Acoustic Scene Classification of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 challenge [1]. This submission departs from the typical application of knowledge distillation from a teacher to a student model, aiming to achieve high performance with limited complexity. The proposed model is based on a CNN-GRU model and is trained solely using the TAU Urban Acoustic Scene 2022 Mobile development dataset [2], without utilizing any external datasets, except for MicIRP [3], which is used for device impulse response (DIR) augmentation. Two models have been submitted to this challenge with memory usage not more than 117 KB and requiring 10.9M multiply-and-accumulate (MAC) operations. Using the development dataset, the proposed model achieved an accuracy of 60.25\%."
}

@techreport{Zhang2025,
    Author = "Zhang, Shuwei and Han, Bing and Jiang, Anbai and Zheng, Xinhu and Zhang, Wei-Qiang and Chen, Xie and Fan, Pingyi and Lu, Cheng and Liu, Jia and Qian, Yanmin",
    title = "Data-Efficient Acoustic Scene Classification via Ensemble Teachers Distillation and Pruning",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "The goal of the acoustic scene classification task is to classify recordings into one of the ten predefined acoustic scene classes. In this report, we describe the submission of the THU-SJTU team for Task 1 Data-Efficient Low-Complexity Acoustic Scene Classification of the DCASE 2025 challenge. Our methods are consistent with those of last year. Firstly, we use an architecture named SSCP-Mobile (spatially separable), which enhances the CP-Mobile with spatially separable convolution structure and achieves lower computation expenses and better performance. Then we adopt several pre-trained PaSST models as ensemble teachers to teach CP-Mobile with knowledge distillation. After that, we use model pruning techniques to trim the model to meet the computational and parameter requirements of the competition. Finally, we will use knowledge distillation techniques again to fine-tune the pruned model and further improve its performance. Due to some reasons, our submissions included four systems that contain only general models, but we also attempted to use device type information to increase the performance of the system S1."
}

@techreport{Ziyang2025,
    Author = "Ziyang, Zhou and Zeyu, Yin and Yiqiang, Cai and Shengchen, Li and Xi, Shao",
    title = "Adaptf-Sepnet: Audioset-Driven Adaptive Pre-Training of Tf-Sepnet for Multi-Device Acoustic Scene Classification",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "May",
    abstract = "This technical report presents our submission to DCASE 2025 Challenge Task 1: Low-Complexity Acoustic Scene Classification with Device Information. We propose a multi-device framework that leverages device-specific models trained with knowledge distillation techniques and enhanced through AudioSet pre-training. Our approach utilizes TF-SepNet as the backbone architecture, pre-trained on the large-scale AudioSet dataset to learn robust acoustic representations. For each of the known devices, a dedicated model is trained. At inference time, the system identifies the device source of the audio clip and selects the corresponding pre-trained model for classification. Evaluated on the test set, our device-specific system achieves an overall accuracy of 59.5\%."
}