@techreport{Cai_ustc_2025,
    author = "Cai, Pengfei and Shi, Yanfeng and Gu, Qing and Jiang, Nan and Song, Yan",
    title = "Parameter-Efficient Tuning of Large Audio-Language Models for DCASE 2025 Challenge Task 5",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "In this technical report, we describe our systems developed for DCASE 2025 Challenge Task5. Our system is mainly based on parameter-efficient tuning of large audio-language models, e.g., Qwen2-Audio and Kimi-Audio. The training process is conducted using Low-Rank Adaptation (LoRA) and divided into two stages: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). In addition, we reformatted the annotations of the AudioSet-Strong and MMAU datasets into a question-answer format to augment the official task dataset. Our final system achieves an accuracy of 80.0\% on the development set."
}

@techreport{Chen_srcn_t5_2025,
    author = "Chen, Minjun and Shao, Jun and Liu, Yangyang and Peng, Bo and Chen, Jie",
    title = "DCASE 2025 Challenge Task 5 Technical Report",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "We describe our submitted systems for DCASE2025 Task 5 in this technical report: Audio Question Answering. Our proposed systems focus on training a Large Audio Language Model (LALM) with carefully curated training datasets and training sessions, based on a carefully chosen multi-modality baseline model. We choose Qwen 2.5 Omni 7B, which has shown impressive performance on audio and vision related tasks, as the base to initialize the audio encoder and LLM component of the proposed systems. We collect and transform multiple audio-text datasets for the training, the total number of samples reached 800K, covering multiple audio related tasks, such as closed Audio QA, opened Audio QA, audio caption, and audio temporal understanding and reasoning. We curated a multi-stage training procedure to help the model learning to focus on different aspects of the data, and to learn from easy to hard during the training process. In the post-training stage, we adopt different training methods, including fine-tune (SFT) and GRPO, to take advantage of their different abilities in generalization and memory. With these carefully considered designs, our model not only learn to answer the questions correctly in content, but also in the required format specified in prompts, which simplify the post-process procedure for evaluation. Our proposed systems achieve top-1 accuracy 81.3\% on the DCASE Task 5 development set"
}

@techreport{Chung_ind_2025,
    author = "Chung, HaeChun",
    title = "Parameter-Efficient Fine-Tuning of Audio Flamingo 2 with LoRA for the DCASE 2025 Audio Question Answering Challenge",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "Audio Question Answering (AQA) presents a significant challenge, demanding models capable of complex reasoning over extensive audio sequences. In this research, we boost the performance of Audio Flamingo 2 (AF2), a compact yet powerful audio-language model, by employing parameter-efficient Low-Rank Adaptation (LoRA). We apply targeted data augmentation strategies for multiple-choice QA and fine-tune the model using the DCASE2025 Challenge Task 5 dataset. Our top-performing model, utilizing LoRA with a rank of 8, achieves a remarkable 69.67\% accuracy. This substantially outperforms all established baselines, including the strong Gemini-2.0-Flash (52.5\%). These results highlight the effectiveness and practical value of lightweight adaptation approach, especially when operating under constrained computational resources"
}

@techreport{Gibier_inria_2025,
    author = {Gibier, Marcel and Celton, Nolwenn and Duroselle, Rapha{\"e}l and Serrano, Pierre and Boeffard, Olivier and Bonastre, Jean-Fran{\c c}ois},
    title = "Audio Question Answering with GRPO-Based Fine-Tuning and Calibrated Segment-Level Predictions",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "In this report, we describe our submission to Track 5 of the DCASE 2025 Challenge for the task of Audio Question Answering (AQA). Our system leverages the SSL backbone BEATs to extract frame-level audio features, which are then processed by a classification head to generate segment-level predictions of acoustic events, following the Audioset ontology. These segment-level predictions are subsequently calibrated before producing event-level predictions. Finally, these predictions are incorporated into a structured prompt, along with the question and candidate answers. This prompt is then fed to a fine-tuned version of Qwen2.5-7B-Instruct, trained using the GRPO algorithm with a simple reward function. Our method achieves a top-1 accuracy of 65.4 \% on the development set, demonstrating the effectiveness of combining acoustic event reasoning with instruction-tuned large language models for AQA."
}

@techreport{He_cuhk_t5_2025,
    author = "He, Haolin and Yang, Mingru and Sun, Renhe and Zhou, Jiayi and Liu, Jian and He, Qianhua and Kong, Qiuqiang",
    title = "Audio Question Answering at the DCASE 2025 Challenge",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "In this technical report, we describe the submission system for DCASE2025 Task 5: Audio Question Answering. In this work, we introduce a comprehensive audio question answering dataset named DCASE-AQA-Boost, featuring diverse question types and carefully curated answer options to address the limitations of existing collections. Based on the DCASE-AQA-Boost, we have developed two models, Kimi-Audio-SFT-12B and Qwen2-Audio-R1-8B. Kimi-Audio-SFT-12B is obtained through a two-stage Supervised Fine-Tuning (SFT) process using the Pretraining and Finetuning split of DCASE-AQA-Boost. Qwen2-Audio-R1-8B is trained using our proposed three-stage training paradigm based on the DCASE-AQA-Boost and DCASE2025 task 5 training set, which incorporates Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO). Experimental results demonstrate that the proposed method significantly improves the accuracy of multiple-choice audio question answering systems. Kimi-Audio-SFT-12B and Qwen2-Audio-R1-8B achieve 77.66\% and 78.18\% accuracy on the DCASE2025 Task 5 development set, respectively."
}

@techreport{Li_mlpxc_2025,
    author = "Li, Gang and Liu, Jizhong and Dinkel, Heinrich and Niu, Yadong and Sun, Xingwei and Wang, Tianzi and Zhang, Junbo and Luan, Jian",
    title = "MIAQA Submission for DCASE 2025 Challenge Task 5: A Reinforcement Learning Driven Audio Question Answering Method",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "This technical report presents an audio question answering (AQA) method submitted to DCASE 2025 Challenge Task 5. Recent studies have shown that reinforcement learning (RL) can enhance the audio reasoning capabilities of large audio language models (LALMs). Thus, we employ a RL strategy to optimize our AQA model. The MiAQA submission is based on our preliminary study [1]1. We apply the group relative policy optimization (GRPO) algorithm to Qwen2.5-Omni-7B. The model directly generates responses after implicit reasoning, without relying on complex, explicit chain-of-thought (CoT). To enhance data diversity, the training data combines human-annotated datasets with weakly labeled datasets generated by large language models (LLMs). Using only a single model and 35k training samples, MiAQA achieves up to 78.0\% accuracy on the DCASE 2025 AQA development set."
}

@techreport{Wijngaard_um_2025,
    author = "Wijngaard, Gijs and Formisano, Elia and Esposito, Michele and Dumontier, Michel",
    title = "Data-Balanced Curriculum Learning for Audio Question Answering",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "Audio question answering (AQA) requires models to understand acoustic content and perform complex reasoning. Current models struggle with dataset imbalances and unstable training dynamics. This work combines curriculum learning with statistical data balancing to address these challenges. The method labels question difficulty using language models, then trains progressively from easy to hard examples. Statistical filtering removes overrepresented audio categories, and guided decoding constrains outputs to valid multiple-choice formats. Experiments on the DCASE 2025 training set and five additional public datasets show that data curation improves accuracy by 19.2\% over baseline models, achieving 64.2\% on the DCASE 2025 benchmark."
}

@techreport{Wojtowicz-Kruk_srpol_2025,
    author = "W{\'o}jtowicz-Kruk, Juliusz and Masztalski, Piotr and Zg{\'o}rzy{\'n}ski, Bart{\l}omiej and Grzeszczyk, Michal",
    title = "Take It with a Grain of Salt: Improving Audio Question Answering with Large Language Models",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "In this report, we present our solution for DCASE 2025 Task 5: Audio Question Answering. We explore two distinct architectures: audio encoder trained with a text decoder model, and the R1-AQA model fine-tuned for the challenge tasks. Our original solution utilizes the PaSST-S audio encoder and the Qwen2.5-1.5B-Instruct model. The model was pre-trained on captioning, tagging, and question answering tasks, followed by fine-tuning for each of the three challenge tasks. The R1-AQA model underwent fine-tuning across all challenge tasks using LoRA. Through experimentation with various datasets and training methodologies, including a few-shot approach, our best trained-from-scratch model achieved an accuracy of 0.61, while the fine-tuned R1-AQA model reached an accuracy of 0.71 on the challenge development split"
}

@techreport{Xiao_heu_2025,
    author = "Xiao, Feiyang and Ye, Tong and Zhang, Kejia and Zhu, Qiaoxi and He, Guangjun and Feng, Pengming and Liu, Li and Wang, Wenwu and Guan, Jian",
    title = "Audio Question Answering Using Audio-Language Model with Supervised Fine-Tuning and Group Relative Policy Optimization",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "This report presents our submission for Task 5 (Audio Question Answering, AQA) of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge. Building on the Qwen-Audio backbone, our system interprets natural language questions and generates textual answers directly from audio inputs. In our submission, an open-source variant of Qwen-Audio-7B with Group Relative Policy optimization (GRPO) is adopted as our first system (GRPO-Qwen), which is then fine-tuned on the DCASE training set with GRPO to obtain our second system (GRPO2). Experiments on the official AQA benchmark show that our systems surpass the baselines in terms of Top-1 accuracy, demonstrating their effectiveness."
}

@techreport{yin_xjtlu_2025,
    author = "Yin, Zeyu and Zhou, Ziyang and Cai, Yiqiang and Li, Shengchen and Shao, Xi",
    title = "EchoTwin-QA: A Dual-Tower BEATsBERT System for DCASE 2025 Task 5 Audio Question Answering",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "Task 5 of the DCASE 2025 Challenge frames Audio Question Answering (AQA) as a multi-choice test of acoustic reasoning across marine bio-acoustics, temporal soundscapes and everyday recordings. We present a light-weight dual-tower system that couples a BEATs-Base audio encoder with a BERT-Base text encoder; a two-layer MLP, amounting to ∼132M trainable parameters, maps the concatenated embeddings to answer logits. On the official development set our best submission achieves 54.46 \% accuracy, surpassing the strongest baseline (Gemini-2.0-Flash, 52.5\%)."
}