# Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning

arXiv: https://arxiv.org/abs/2009.11436 · HTML: https://mlsanity.com/paper/2009.11436/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation](https://mlsanity.com/paper/2103.06695/) (2021)
- [Audio Captioning Transformer](https://mlsanity.com/paper/2107.09817/) (2021)
- [UnIVAL: Unified Model for Image, Video, Audio and Language Tasks](https://mlsanity.com/paper/2307.16184/) (2023)
- [Automated Audio Captioning: An Overview of Recent Progress and New Challenges](https://mlsanity.com/paper/2205.05949/) (2022)
- [CL4AC: A Contrastive Loss for Audio Captioning](https://mlsanity.com/paper/2107.09990/) (2021)
- [DECAR: Deep Clustering for learning general-purpose Audio Representations](https://mlsanity.com/paper/2110.08895/) (2021)
- [Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning](https://mlsanity.com/paper/2110.07410/) (2021)
- [Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach](https://mlsanity.com/paper/2107.08028/) (2021)
- [Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement](https://mlsanity.com/paper/2308.11923/) (2023)
- [DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning](https://mlsanity.com/paper/2203.13628/) (2022)
- [Introducing Auxiliary Text Query-modifier to Content-based Audio Retrieval](https://mlsanity.com/paper/2207.09732/) (2022)
- [UNFUSED: UNsupervised Finetuning Using SElf supervised Distillation](https://mlsanity.com/paper/2303.05668/) (2023)

## Abstract (arXiv)

The system we used for Task 6 (Automated Audio Captioning)of the Detection and Classification of Acoustic Scenes and Events(DCASE) 2020 Challenge combines three elements, namely, dataaugmentation, multi-task learning, and post-processing, for audiocaptioning. The system received the highest evaluation scores, butwhich of the individual elements most fully contributed to its perfor-mance has not yet been clarified. Here, to asses their contributions,we first conducted an element-wise ablation study on our systemto estimate to what extent each element is effective. We then con-ducted a detailed module-wise ablation study to further clarify thekey processing modules for improving accuracy. The results showthat data augmentation and post-processing significantly improvethe score in our system. In particular, mix-up data augmentationand beam search in post-processing improve SPIDEr by 0.8 and 1.6points, respectively.