@techreport{Cai2025_t6,
    Author = "Cai, Xichang and Luo, Weijie",
    title = "Dual-Encoder Audio Retrieval with PaSST and RoBERTa: A Contrastive and Distillation Approach",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "This technical report describes the Cai\_NCUT team's submissions to the language-based audio retrieval task of the 2025 DCASE Challenge (Task 6). Our systems are built upon the dual encoder architecture, mapping audio clips and textual queries into a joint embedding space using pretrained backbones. In this submission, we explore the use of the recently proposed Time-Aware Spectrogram Transformer (PASST) as the audio encoder and RoBERTa as the text encoder. We introduce a two-stage training pipeline involving contrastive learning and a self-distillation phase to leverage cross-modal soft alignments. Our best single system, based on PASST and RoBERTa-large, achieves a mAP@16 of 0.32 on the ClothoV2 test split."
}

@techreport{Calvet2025_t6,
    Author = "Calvet, Oscar and Torre, Doroteo",
    title = "A CROSS-MODAL ATTENTION APPROACH TO LANGUAGE-BASED AUDIO RETRIEVAL",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "This report presents the systems we developed for the 2025 DCASE Language-Based Audio Retrieval challenge (task 6). We use a bi-encoder architecture and propose a novel cross modal attention approach in order to calculate the similarity between the embeddings produced by both models. We make use of pretrained encoders in both modalities: PaSST is used for encoding audio and RoBERTa for encoding text. We trained our system on WavCaps, AudioCaps, ClothoV2 and TACOS using contrastive learning. The best single system that we were able to produce reaches a mAP@10 of 38.293 on the ClothoV2 test split and a mAP@16 of 44.203 using the task specific improved notations. An ensemble of the models presented archieves a mAP@10 of 40.423 on the ClothoV2 test split and a mAP@16 of 46.864 using the task specific improved notations."
}

@techreport{Filomeno2025_t6,
    Author = "Filomeno, Giovanni and Kandah, Youssef and Spiessberger, Florian",
    title = "ENHANCING LANGUAGE-BASED AUDIO RETRIEVAL WITH PARTIAL FINE-TUNING AND ATTENTION POOLING",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "This technical report describes our submission to the language-based audio retrieval task of the DCASE 2025 Challenge (Task 6). Building upon our previous work, we retain the dual-encoder architecture that projects audio recordings and textual descriptions into a shared embedding space. This year we focus on architectural and training-level refinements within a single model framework. Specifically, we fine-tune only the upper transformer layers of a PaSST audio encoder, apply attention-based segment pooling, and replace CLS token extraction in RoBERTa with masked mean pooling. Additionally, we introduce time-frequency spectrogram augmentation and reduce the hop size to capture more segment detail. Our improved system achieves a mAP@10 of 36.005 on the ClothoV2 test set, outperforming the official DCASE 2025 baseline without relying on external caption generation or model ensembles. The result for mAP@16 as requested this year is 36.661 (without new annotations). All code and trained models are available on GitHub."
}

@techreport{Kim2025_t6,
    Author = "Kim, Hyun Jun and Choi, Hyeong Yong and Choi, Kyuwon and Choi, Eunsin and Lim, Changwon",
    title = "AISTAT LAB SYSTEM FOR DCASE 2025 TASK6: LANGUAGE-BASED AUDIO RETREIVAL",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "This report presents the AISTAT team's submission to the language-based audio retrieval task in DCASE 2025 Task 6. Our proposed system employs dual encoder architecture, where audio and text modalities are encoded separately, and their representations are aligned using contrastive learning. Drawing inspiration from methodologies of the previous year's challenge, we implemented a distillation approach and leveraged large language models (LLMs) for effective data augmentation techniques, including back-translation and LLM mix. Additionally, we incorporated pseudo-labeling to introduce a classification auxiliary task for further finetuning. Our best single system achieved a mAP@16 of 46.5, while an ensemble of four systems reaches a mAP@16 of 48.83 on the Clotho development test split."
}

@techreport{Pandey2025_t6,
    Author = "Pandey, Saubhagya and Wadhwa, Khushal and Goyal, Ayush and Khandelwal, Kanak",
    title = "Enhanced Audio-Text Retrieval with Multi-Positive Learning and Hard Negative Mining",
    institution = "DCASE2025 Challenge",
    year = "2025",
    month = "June",
    abstract = "This paper presents an enhanced implementation of audio-text cross-modal retrieval for DCASE 2025 Task 6, featuring advanced contrastive learning techniques. Our system implements a dual-encoder architecture using PaSST (Patch-out Fast Spectrogram Transformer) for audio encoding and RoBERTa-large for text encoding, enhanced with multi-positive learning and hard negative mining strategies. The proposed method introduces progressive training with staged activation of advanced techniques, achieving significant performance improvements over baseline approaches. Experimental evaluation on the Clotho dataset demonstrates competitive retrieval performance with R@1 of 18.68\%, R@5 of 44.77\%, R@10 of 59.35\%, and mAP@10 of 30.01\%. The implementation supports mixed precision training and comprehensive evaluation metrics for robust cross-modal retrieval."
}