Dataset Groups Activity Stream WavCaps The WavCaps dataset contains chatGPT-assisted weakly-labeled audio captioning data. BibTex: @dataset{Andrea_Agostinelli_and_Timo_I_Denk_and_Zalán_Borsos_and_Jesse_Engel_and_Mauro_Verzetti_and_Antoine_Caillon_and_Qingqing_Huang_and_Aren_Jansen_and_Adam_Roberts_and_Marco_Tagliasacchi_2024, abstract = {The WavCaps dataset contains chatGPT-assisted weakly-labeled audio captioning data.}, author = {Andrea Agostinelli and Timo I Denk and Zalán Borsos and Jesse Engel and Mauro Verzetti and Antoine Caillon and Qingqing Huang and Aren Jansen and Adam Roberts and Marco Tagliasacchi}, doi = {10.57702/rgvde92y}, institution = {No Organization}, keyword = {'Audio', 'Captioning', 'Weakly Supervised', 'audio captioning', 'large-scale', 'multimodal learning', 'weakly-labeled', 'weakly-supervised learning'}, month = {dec}, publisher = {TIB}, title = {WavCaps}, url = {https://service.tib.eu/ldmservice/dataset/wavcaps}, year = {2024} }
