# A bandit approach to curriculum generation for automatic speech recognition

arXiv: https://arxiv.org/abs/2102.03662 · HTML: https://mlsanity.com/paper/2102.03662/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 6 Feb 2021.

## Builds on (most cited first, 6 of 6)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition](https://mlsanity.com/paper/1606.06864/) (2016)
- [Improved training for online end-to-end speech recognition systems](https://mlsanity.com/paper/1711.02212/) (2017)
- [Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection](https://mlsanity.com/paper/1711.03689/) (2017)

## Built on by (most cited first, 2 of 2)

- [Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook](https://mlsanity.com/paper/2210.13623/) (2022)
- [Representative Arm Identification: A fixed confidence approach to identify cluster representatives](https://mlsanity.com/paper/2408.14195/) (2024)

## Abstract (arXiv)

The Automated Speech Recognition (ASR) task has been a challenging domain especially for low data scenarios with few audio examples. This is the main problem in training ASR systems on the data from low-resource or marginalized languages. In this paper we present an approach to mitigate the lack of training data by employing Automated Curriculum Learning in combination with an adversarial bandit approach inspired by Reinforcement learning. The goal of the approach is to optimize the training sequence of mini-batches ranked by the level of difficulty and compare the ASR performance metrics against the random training sequence and discrete curriculum. We test our approach on a truly low-resource language and show that the bandit framework has a good improvement over the baseline transfer-learning model.