Graph Attention for Automated Audio Captioning
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2023.3266114
Abstract: State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing the long-time dependencies within… read more here.
Keywords: automated audio; audio captioning; attention automated; graph attention ... See more keywords