Advancing Natural-language Based Audio Retrieval With Passt And Large Audio-caption Data Sets

Abstract

This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our method projects recordings and textual descriptions into a shared audio-caption space in which related examples from different modalities are close. Through a systematic analysis, we examine how each component of the system influences retrieval performance. As a result, we identify two key components that play a crucial role in driving performance: the self-attention-based audio encoder for audio embedding and the utilization of additional human-generated and synthetic data sets during pre-training. We further experimented with augmenting ClothoV2 captions with available keywords to increase their variety; however, this only led to marginal improvements. Our system ranked first in the 2023's DCASE Challenge, and it outperforms the current state of the art on the ClothoV2 benchmark by 5.6 pp. mAP@10.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyprimus2023advancing

Related papers

• Improving Natural-language-based Audio Retrieval With Transfer Learning And Audio & Text Augmentations (2022)0.00
• RECAP: Retrieval-augmented Audio Captioning (2023)9.41
• Automated Audio Captioning And Language-based Audio Retrieval (2022)0.00
• Audio Captioning Using Pre-trained Large-scale Language Model Guided By Audio-based Similar Caption Retrieval (2020)0.00
• Audiosetcaps: An Enriched Audio-caption Dataset Using Automated Generation Pipeline With Large Audio And Language Models (2024)13.44
• Enhancing Retrieval-augmented Audio Captioning With Generation-assisted Multimodal Querying And Progressive Learning (2024)3.58
• An Encoder-decoder Based Audio Captioning System With Transfer And Reinforcement Learning (2021)0.00
• Learning Audio-video Modalities From Image Captions (2022)12.54