Listen carefully and tell: an audio captioning system based on residual learning and gammatone audio representation
This work addresses the problem of generating textual descriptions from audio for applications like content description, but it appears incremental as it builds on existing methods.
The authors tackled automated audio captioning by proposing a system using residual learning in the encoder phase with Gammatone audio representation, and it surpassed baseline results in challenge evaluations.
Automated audio captioning is machine listening task whose goal is to describe an audio using free text. An automated audio captioning system has to be implemented as it accepts an audio as input and outputs as textual description, that is, the caption of the signal. This task can be useful in many applications such as automatic content description or machine-to-machine interaction. In this work, an automatic audio captioning based on residual learning on the encoder phase is proposed. The encoder phase is implemented via different Residual Networks configurations. The decoder phase (create the caption) is run using recurrent layers plus attention mechanism. The audio representation chosen has been Gammatone. Results show that the framework proposed in this work surpass the baseline system in challenge results.