# Curriculum optimization for low-resource speech recognition

arXiv: https://arxiv.org/abs/2202.08883 · HTML: https://mlsanity.com/paper/2202.08883/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 17 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [Norm-Based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/2006.02014/) (2020)
- [Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling](https://mlsanity.com/paper/1810.03459/) (2018)
- [Reinforcement Learning based Curriculum Optimization for Neural Machine Translation](https://mlsanity.com/paper/1903.00041/) (2019)
- [A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition](https://mlsanity.com/paper/1606.06864/) (2016)
- [On Abruptly-Changing and Slowly-Varying Multiarmed Bandit Problems](https://mlsanity.com/paper/1802.08380/) (2018)
- [Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition](https://mlsanity.com/paper/2012.11896/) (2020)
- [Improved training for online end-to-end speech recognition systems](https://mlsanity.com/paper/1711.02212/) (2017)
- [Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation](https://mlsanity.com/paper/1805.00178/) (2018)
- [Dynamic curriculum learning via data parameters for noise robust keyword spotting](https://mlsanity.com/paper/2102.09666/) (2021)

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

- [Comparison and Analysis of New Curriculum Criteria for End-to-End ASR](https://mlsanity.com/paper/2208.05782/) (2022)

## Abstract (arXiv)

Modern end-to-end speech recognition models show astonishing results in transcribing audio signals into written text. However, conventional data feeding pipelines may be sub-optimal for low-resource speech recognition, which still remains a challenging task. We propose an automated curriculum learning approach to optimize the sequence of training examples based on both the progress of the model while training and prior knowledge about the difficulty of the training examples. We introduce a new difficulty measure called compression ratio that can be used as a scoring function for raw audio in various noise conditions. The proposed method improves speech recognition Word Error Rate performance by up to 33% relative over the baseline system