AISTAT lab system for DCASE2025 Task6: Language-based audio retrieval
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 clustering to introduce an auxiliary classification task for further finetuning. Our best single system achieved a mAP@16 of 46.62, while an ensemble of four systems reached a mAP@16 of 48.83 on the Clotho development test split.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningData AugmentationSimilar Papers 제목 키워드 기반
Language-based Audio Retrieval Task in DCASE 2022 Challenge
Language-based audio retrieval is a task, where natural language textual captions are used as queries to retrieve audio signals from a dataset. It has been first introduced into DCASE 2022 Challenge as Subtask 6B of task…
Audio captioningRetrievalLanguage-based Audio Retrieval Task in DCASE 2022 Challenge
Language-based audio retrieval is a task, where natural language textual captions are used as queries to retrieve audio signals from a dataset. It has been first introduced into DCASE 2022 Challenge as Subtask 6B of task…
Audio captioningRetrievalMulti-Domain Audio Question Answering Toward Acoustic Content Reasoning in The DCASE 2025 Challenge
We present Task 5 of the DCASE 2025 Challenge: an Audio Question Answering (AQA) benchmark spanning multiple domains of sound understanding. This task defines three QA subsets (Bioacoustics, Temporal Soundscapes, and Com…
Audio Question AnsweringQuestion AnsweringGeneral audio tagging with ensembling convolutional neural network and statistical features
Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general au…
Audio TaggingDescriptiveEnsemble LearningTask 2Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results
As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of …
Event DetectionGeneral ClassificationSound Event Detection