REVIEW 4 cited by
WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming collection process of existing audio-language datasets, which are limited in size. To address this data scarcity issue, we introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. We sourced audio clips and their raw descriptions from web sources and a sound event detection dataset. However, the online-harvested raw descriptions are highly noisy and unsuitable for direct use in tasks such as automated audio captioning. To overcome this issue, we propose a three-stage processing pipeline for filtering noisy data and generating high-quality captions, where ChatGPT, a large language model, is leveraged to filter and transform raw descriptions automatically. We conduct a comprehensive analysis of the characteristics of WavCaps dataset and evaluate it on multiple downstream audio-language multimodal learning tasks. The systems trained on WavCaps outperform previous state-of-the-art (SOTA) models by a significant margin. Our aspiration is for the WavCaps dataset we have proposed to facilitate research in audio-language multimodal learning and demonstrate the potential of utilizing ChatGPT to enhance academic research. Our dataset and codes are available at https://github.com/XinhaoMei/WavCaps.
Forward citations
Cited by 4 Pith papers
-
Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio
Trained connectors and audio-only gated adapters integrate audio into a frozen vision-language embedding space, preserving base outputs bit-exactly and yielding emergent audio-image retrieval.
-
Discriminative Axis, Not Data Volume: What a Contrastive Corpus Teaches an Audio Embedding
A contrastive audio embedding learns an attribute only when in-batch negatives cannot be separated without it, so corpus structure, not size or caption vocabulary, controls what is encoded.
-
The iNaturalist Sounds Dataset
A new large-scale, weakly labeled audio dataset of 230K recordings across 5,569 species, with benchmarks showing that models trained on it transfer to downstream bioacoustic classification.
-
Quantum Computing : A New Frontier for Science and Society
A review surveying quantum computing hardware platforms, control layers, error correction, and software stacks as of 2023–2025.
Discussion (0). Continue with ORCID to comment.