paper-with-me

홈 › Papers

AISTAT lab system for DCASE2025 Task6: Language-based audio retrieval

2025-09-20 · Hyun Jun Kim, Hyeong Yong Choi, Changwon Lim arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.16649

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningData Augmentation

Similar Papers 제목 키워드 기반

Language-based Audio Retrieval Task in DCASE 2022 Challenge

2022-06-13 · Huang Xie, Samuel Lipping, Tuomas Virtanen

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 captioningRetrieval

Language-based Audio Retrieval Task in DCASE 2022 Challenge

2022-09-20 · Huang Xie, Samuel Lipping, Tuomas Virtanen

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 captioningRetrieval

Multi-Domain Audio Question Answering Toward Acoustic Content Reasoning in The DCASE 2025 Challenge

2025-05-12 · Chao-Han Huck Yang, Sreyan Ghosh, Qing Wang, Jaeyeon Kim 외

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 Answering

General audio tagging with ensembling convolutional neural network and statistical features

2018-10-30 · Kele Xu, Boqing Zhu, Qiuqiang Kong, Haibo Mi 외

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 2

Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results

2017-11-15 · Grégoire Lafay, Emmanouil Benetos, Mathieu Lagrange

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