@techreport{Cai2024_t8,
    Author = "Li, Jiafeng and Cai, Xichang and Liu, Shenghao and Zuo, Liangxiao and Wu, Menglong",
    title = "ENSEMBLE SYSTEMS WITH PRETRAINED DUAL-ENCODERS FOR LANGUAGE-BASED AUDIO RETRIEVAL",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "June",
    abstract = "This article presents our system developed for Task 8 of the DCASE2024 Challenge, which focuses on audio retrieval using natural language queries. Our submission incorporates a retrieval system that integrates a frozen pre-trained audio encoder and RoBERT as a text encoder. We adopted a methodology similar to the CLAP framework, training our model using paired data from the AudioCaps and Clotho datasets. Our best-performing system achieved a mean Average Precision (mAP) of 29.6\% and a Recall at 1 (R@1) of 18.6\% on the Clotho evaluation set."
}

@techreport{Chen2024_t8,
    Author = "Chen, Minjun and Liu, Yangyang and Peng, Bo and Chen, Jie",
    title = "DCASE 2024 CHALLENGE TASK 8 TECHNICAL REPORT",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "June",
    abstract = "We describe our submitted systems for DCASE2024 Task 8 in this technical report: Language-based Audio Retrieval. Our proposed system focus on training audio encoder and text encoder combined to get expressive audio and text presentation, which helps distinguishing different audios and text more efficiently. We use pre-trained audio and text encoder of VAST, which were trained on a large multi-modality dataset VAST27M. We train these encoders on several audio caption datasets, include AudioCaps, WavCaps, FSD50K, Laion630k, and ClothoV2 furtherly with three learning objectives, except the audio-text contractive objective, we also use audio-text match and masked language model objective to strengthen the training procedure. We use the mix-up as the data augment policy during pre-training. Our proposed systems achieve 0.37 mAP@10, and 0.244 R@1, with model ensemble, our systems achieve 0.406 mAP@10, and 0.278 R@1 on the ClothoV2 evaluation set."
}

@techreport{Kim2024_t8,
    Author = "Kim, Jaeyeon and Jung, Jaeyoon and Jeon, Minjeong and Woo, Sang Hoon and Lee, Jinjoo",
    title = "EXPANDING ON ENCLAP WITH AUXILIARY RETRIEVAL MODEL FOR AUTOMATED AUDIO CAPTIONING",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "June",
    abstract = "In this technical report, we describe our submission to DCASE2024 Challenge Task6 (Automated Audio Captioning) and Task8 (Language-based Audio Retrieval). We develop our approach building upon the EnCLAP audio captioning framework and optimizing it for Task6 of the challenge. Notably, we outline the changes in the underlying components and the incorporation of the reranking process. Additionally, we submit a supplementary retriever model, a byproduct of our modified framework, to Task8. Our proposed systems achieve FENSE score of 0.542 on Task6 and mAP@10 score of 0.386 on Task8, significantly outperforming the baseline models."
}

@techreport{Kulik2024_t8,
    Author = "Kulik, Jan and Zgorzynski, Bartlomiej and Kruk, Juliusz and Ryzhankow, Ivan and Ples, Anna and de Gail, Theodore Lamort",
    title = "TAKE IT FOR GRANTED: IMPROVING LANGUAGE-BASED AUDIO RETRIEVAL WITH LARGE LANGUAGE MODELS",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "June",
    abstract = "In this report, we present our solution to DCASE 2024 task 8: Language-Based Audio Retrieval. We employ a bi-encoder architecture trained using InfoNCE loss. The audio encoder is a pretrained PaSST-S model, while the text encoder is either a pre-trained GTE-large or RoBERTa-large model. In order to increase the amount of training data, we obtain 10.8 million video-caption pairs from various open-source datasets. We then extract useful audio-caption pairs and evaluate them using our model to filter out low-quality samples. Finally, we use GPT-4o to rephrase the video captions to make them more audio-oriented. In addition, we use GPT-4o for back-translation and GPT-3.5-turbo for Clotho caption mixing. We achieve 43.69\% mAP@10 on the development-testing split of Clotho using an ensemble solution, and 40.78\% mAP@10 with a single model."
}

@techreport{Munakata2024_t8,
    Author = "Munakata, Hokuto and Nishimura, Taichi and Nakada, Shota and Komatsu, Tatsuya",
    title = "TRAINING STRATEGY OF MASSIVE TEXT-TO-AUDIO MODELS AND GPT-BASED QUERY-AUGMENTATION",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "June",
    abstract = "This report describes our system submitted to the DCASE 2024 Task 8: Language-based Audio Retrieval. We adopted a conventional language-based audio retrieval approach, leveraging a joint embedding space for the audio and text encoders trained through contrastive learning. We compared and utilized several state-ofthe-art models for the audio encoder, including PaSST, BEATs, VAST, and CAV-MAE. We also employed various datasets with text-audio pairs for training like AudioCaps, WavCaps, Auto-ACD, and MACS. Additionally, we incorporated advanced training techniques such as Mixco and text token masking. During inference, we devised an ensemble method based on queries augmented by ChatGPT. Our final results achieved 39.65 points with a single model and 42.26 points with the ensemble of multiple models in the mean average precision among the top 10 results on the evaluation split of Clotho-V2. Compared with the champion system of the DCASE 2023 Challenge, our model outperformed by 1.09 points for the single mode and 0.84 points for the ensemble of the multiple models, respectively."
}

@techreport{Primus2024_t8,
    Author = "Primus, Paul and Widmer, Gerhard",
    title = "A KNOWLEDGE DISTILLATION APPROACH TO IMPROVING LANGUAGE-BASED AUDIO RETRIEVAL MODELS",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "June",
    abstract = "This technical report describes the CP-JKU team’s submissions to the language-based audio retrieval task of the 2024 DCASE Challenge (Task 8). All our submitted systems are based on the dual encoder architecture that projects recordings and textual descriptions into a shared audio-caption space in which related examples from the two modalities are similar. We utilized pretrained audio and text embedding models and trained them on audio-caption datasets (WavCaps, AudioCaps, and ClothoV2) via contrastive learning. We further fine-tuned the resulting models on ClothoV2 via knowledge distillation from a large ensemble of audio retrieval models. Our best single system submission based on PaSST and RoBERTa achieves a mAP@10 of 39.77 on the ClothoV2 test split, outperforming last year’s best single system submission by around 1pp. without utilizing metadata and synthetic captions. An ensemble of three distilled models achieves 41.91 mAP@10 on the ClothoV2 test split."
}