Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning
This work addresses the challenge of generating descriptive captions for audio clips, which is incremental as it builds on existing encoder-decoder architectures by incorporating hierarchical topic analysis and transfer learning.
The paper tackled the problem of automated audio captioning by proposing a topic model and a transfer learning scheme that leverages local and global information from audio tagging and acoustic scene classification, resulting in a vast increase in all eight metrics on benchmark datasets Clotho and Audiocaps.
Automated audio captioning (AAC) aims at generating summarizing descriptions for audio clips. Multitudinous concepts are described in an audio caption, ranging from local information such as sound events to global information like acoustic scenery. Currently, the mainstream paradigm for AAC is the end-to-end encoder-decoder architecture, expecting the encoder to learn all levels of concepts embedded in the audio automatically. This paper first proposes a topic model for audio descriptions, comprehensively analyzing the hierarchical audio topics that are commonly covered. We then explore a transfer learning scheme to access local and global information. Two source tasks are identified to respectively represent local and global information, being Audio Tagging (AT) and Acoustic Scene Classification (ASC). Experiments are conducted on the AAC benchmark dataset Clotho and Audiocaps, amounting to a vast increase in all eight metrics with topic transfer learning. Further, it is discovered that local information and abstract representation learning are more crucial to AAC than global information and temporal relationship learning.