# Self-paced ensemble learning for speech and audio classification

arXiv: https://arxiv.org/abs/2103.11988 · HTML: https://mlsanity.com/paper/2103.11988/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 40 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Curriculum Self-Paced Learning for Cross-Domain Object Detection](https://mlsanity.com/paper/1911.06849/) (2019)
- [Self-paced Ensemble for Highly Imbalanced Massive Data Classification](https://mlsanity.com/paper/1909.03500/) (2019)
- [Self Paced Deep Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1605.07651/) (2016)
- [Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)](https://mlsanity.com/paper/1910.08967/) (2019)
- [Deep Self-Paced Learning for Person Re-Identification](https://mlsanity.com/paper/1710.05711/) (2017)
- [Visually Guided Self Supervised Learning of Speech Representations](https://mlsanity.com/paper/2001.04316/) (2020)
- [Non-linear Neurons with Human-like Apical Dendrite Activations](https://mlsanity.com/paper/2003.03229/) (2020)
- [Are you wearing a mask? Improving mask detection from speech using augmentation by cycle-consistent GANs](https://mlsanity.com/paper/2006.10147/) (2020)
- [Pixel-Level Self-Paced Learning for Super-Resolution](https://mlsanity.com/paper/2003.03113/) (2020)

## Built on by (most cited first, 11 of 11)

- [SepTr: Separable Transformer for Audio Spectrogram Processing](https://mlsanity.com/paper/2203.09581/) (2022)
- [Learning Rate Curriculum](https://mlsanity.com/paper/2205.09180/) (2022)
- [Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation](https://mlsanity.com/paper/2402.12862/) (2024)
- [CBM: Curriculum by Masking](https://mlsanity.com/paper/2407.05193/) (2024)
- [Evaluating raw waveforms with deep learning frameworks for speech emotion recognition](https://mlsanity.com/paper/2307.02820/) (2023)
- [Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles](https://mlsanity.com/paper/2310.11379/) (2023)
- [Self-paced learning to improve text row detection in historical documents with missing labels](https://mlsanity.com/paper/2201.12216/) (2022)
- [On Spectrogram Analysis in a Multiple Classifier Fusion Framework for Power Grid Classification Using Electric Network Frequency](https://mlsanity.com/paper/2403.18402/) (2024)
- [CL4KGE: A Curriculum Learning Method for Knowledge Graph Embedding](https://mlsanity.com/paper/2408.14840/) (2024)
- [Structural and Statistical Audio Texture Knowledge Distillation for Acoustic Classification](https://mlsanity.com/paper/2501.01921/) (2025)
- [Toward Efficient Speech Emotion Recognition via Spectral Learning and Attention](https://mlsanity.com/paper/2507.03251/) (2025)

## Abstract (arXiv)

Combining multiple machine learning models into an ensemble is known to provide superior performance levels compared to the individual components forming the ensemble. This is because models can complement each other in taking better decisions. Instead of just combining the models, we propose a self-paced ensemble learning scheme in which models learn from each other over several iterations. During the self-paced learning process based on pseudo-labeling, in addition to improving the individual models, our ensemble also gains knowledge about the target domain. To demonstrate the generality of our self-paced ensemble learning (SPEL) scheme, we conduct experiments on three audio tasks. Our empirical results indicate that SPEL significantly outperforms the baseline ensemble models. We also show that applying self-paced learning on individual models is less effective, illustrating the idea that models in the ensemble actually learn from each other.