Clotho
Emerging7papers using it
2021first seen
Clotho is a dataset used for evaluating language-based audio retrieval systems, containing audio clips paired with descriptive text.
Papers using Clotho (7)
- GLAP: General contrastive audio-text pretraining across domains and languagesFORTE: FOL-guided Optimal Refinement for Text-audio rEtrievalAISTAT lab system for DCASE2025 Task6: Language-based audio retrievalImproving the Performance of Automated Audio Captioning via Integrating
the Acoustic and Semantic InformationAutomated Audio Captioning using Transfer Learning and Reconstruction
Latent Space Similarity RegularizationEnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for
Automated Audio CaptioningLanguage-based Audio Retrieval with Co-Attention Networks