# A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition

arXiv: https://arxiv.org/abs/2007.00144 · HTML: https://mlsanity.com/paper/2007.00144/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

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

- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks](https://mlsanity.com/paper/2110.07313/) (2021)
- [Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices](https://mlsanity.com/paper/2103.03483/) (2021)
- [Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices](https://mlsanity.com/paper/2108.06128/) (2021)
- [Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block](https://mlsanity.com/paper/2211.02940/) (2022)
- [Do sound event representations generalize to other audio tasks? A case study in audio transfer learning](https://mlsanity.com/paper/2106.11335/) (2021)
- [Study of positional encoding approaches for Audio Spectrogram Transformers](https://mlsanity.com/paper/2110.06999/) (2021)
- [CORN: Co-Trained Full- And No-Reference Speech Quality Assessment](https://mlsanity.com/paper/2310.09388/) (2023)
- [Conditional Teaching Size](https://mlsanity.com/paper/2107.07038/) (2021)
- [Responding to Challenge Call of Machine Learning Model Development in Diagnosing Respiratory Disease Sounds](https://mlsanity.com/paper/2111.14354/) (2021)
- [Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study](https://mlsanity.com/paper/2202.03514/) (2022)
- [CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment](https://mlsanity.com/paper/2211.02577/) (2022)

## Abstract (arXiv)

An important problem in machine auditory perception is to recognize and detect sound events. In this paper, we propose a sequential self-teaching approach to learning sounds. Our main proposition is that it is harder to learn sounds in adverse situations such as from weakly labeled and/or noisy labeled data, and in these situations a single stage of learning is not sufficient. Our proposal is a sequential stage-wise learning process that improves generalization capabilities of a given modeling system. We justify this method via technical results and on Audioset, the largest sound events dataset, our sequential learning approach can lead to up to 9% improvement in performance. A comprehensive evaluation also shows that the method leads to improved transferability of knowledge from previously trained models, thereby leading to improved generalization capabilities on transfer learning tasks.