# CHUCKLE -- When Humans Teach AI To Learn Emotions The Easy Way

arXiv: https://arxiv.org/abs/2510.09382 · HTML: https://mlsanity.com/paper/2510.09382/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Understanding the Difficulty of Training Transformers](https://mlsanity.com/paper/2004.08249/) (2020)
- [Survey on Emotional Body Gesture Recognition](https://mlsanity.com/paper/1801.07481/) (2018)
- [Hybrid Curriculum Learning for Emotion Recognition in Conversation](https://mlsanity.com/paper/2112.11718/) (2021)
- [A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition](https://mlsanity.com/paper/1606.06864/) (2016)
- [Curriculum Learning for Speech Emotion Recognition from Crowdsourced Labels](https://mlsanity.com/paper/1805.10339/) (2018)

## Built on by (most cited first, 1 of 1)

- [SPICE: Synergy and Partial Information Based Curriculum Evolution](https://mlsanity.com/paper/2606.16639/) (2026)

## Abstract (arXiv)

Curriculum learning (CL) structures training from simple to complex samples, facilitating progressive learning. However, existing CL approaches for emotion recognition often rely on heuristic, data-driven, or model-based definitions of sample difficulty, neglecting the difficulty for human perception, a critical factor in subjective tasks like emotion recognition. We propose CHUCKLE (Crowdsourced Human Understanding Curriculum for Knowledge Led Emotion Recognition), a perception-driven CL framework that leverages annotator agreement and alignment in crowd-sourced datasets to define sample difficulty, under the assumption that clips challenging for humans are similarly hard for neural networks. Experimental results suggest that CHUCKLE enhances the performance of LSTMs and Transformers over non-curriculum baselines, while reducing the number of gradient updates, thereby enhancing both training efficiency and model robustness in both subject-dependent and subject-independent settings.