# Accented Speech Recognition Inspired by Human Perception

arXiv: https://arxiv.org/abs/2104.04627 · HTML: https://mlsanity.com/paper/2104.04627/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [Learning Fast Adaptation on Cross-Accented Speech Recognition](https://mlsanity.com/paper/2003.01901/) (2020)
- [From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition](https://mlsanity.com/paper/1910.01493/) (2019)
- [REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling](https://mlsanity.com/paper/2012.07353/) (2020)
- [Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks](https://mlsanity.com/paper/1301.3605/) (2013)
- [Black-box Adaptation of ASR for Accented Speech](https://mlsanity.com/paper/2006.13519/) (2020)

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

- [Accented Speech Recognition With Accent-specific Codebooks](https://mlsanity.com/paper/2310.15970/) (2023)

## Abstract (arXiv)

While improvements have been made in automatic speech recognition performance over the last several years, machines continue to have significantly lower performance on accented speech than humans. In addition, the most significant improvements on accented speech primarily arise by overwhelming the problem with hundreds or even thousands of hours of data. Humans typically require much less data to adapt to a new accent. This paper explores methods that are inspired by human perception to evaluate possible performance improvements for recognition of accented speech, with a specific focus on recognizing speech with a novel accent relative to that of the training data. Our experiments are run on small, accessible datasets that are available to the research community. We explore four methodologies: pre-exposure to multiple accents, grapheme and phoneme-based pronunciations, dropout (to improve generalization to a novel accent), and the identification of the layers in the neural network that can specifically be associated with accent modeling. Our results indicate that methods based on human perception are promising in reducing WER and understanding how accented speech is modeled in neural networks for novel accents.