WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information
- 1. Audio Research Group, Tampere University, Finland
Description
Automated audio captioning (AAC) is a novel task, where a method takes as an input an audio sample and outputs a textual description (i.e. a caption) of its contents. Most AAC methods are adapted from image captioning or machine translation fields. In this work, we present a novel AAC method, explicitly focused on the exploitation of the temporal and time-frequency patterns in audio. We employ three learnable processes for audio encoding, two for extracting the temporal and time-frequency information, and one to merge the output of the previous two processes. To generate the caption, we employ the widely used Transformer decoder. We assess our method utilizing the freely available splits of the Clotho dataset. Our results increase previously reported highest SPIDEr to 17.3, from 16.2 (higher is better).
Notes
Files
EUSIPCO2021_Tran_et_al_WaveTransformer.pdf
Files
(236.0 kB)
Name | Size | Download all |
---|---|---|
md5:62a2d9b7b4673ce9ddc879fe376ab412
|
236.0 kB | Preview Download |
Additional details
Related works
- Is supplemented by
- Software: https://github.com/haantran96/wavetransformer (URL)
- Dataset: 10.5281/zenodo.4783391 (DOI)