# Multi-Accent Adaptation based on Gate Mechanism

arXiv: https://arxiv.org/abs/2011.02774 · HTML: https://mlsanity.com/paper/2011.02774/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech](https://mlsanity.com/paper/2109.06952/) (2021)
- [Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets](https://mlsanity.com/paper/2110.04612/) (2021)
- [Accented Speech Recognition: A Survey](https://mlsanity.com/paper/2104.10747/) (2021)
- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)
- [Improving the Training Recipe for a Robust Conformer-based Hybrid Model](https://mlsanity.com/paper/2206.12955/) (2022)
- [Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR](https://mlsanity.com/paper/2110.04484/) (2021)
- [AfriNames: Most ASR models "butcher" African Names](https://mlsanity.com/paper/2306.00253/) (2023)
- [On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech](https://mlsanity.com/paper/2106.10259/) (2021)
- [A meta learning scheme for fast accent domain expansion in Mandarin speech recognition](https://mlsanity.com/paper/2307.12262/) (2023)

## Abstract (arXiv)

When only a limited amount of accented speech data is available, to promote multi-accent speech recognition performance, the conventional approach is accent-specific adaptation, which adapts the baseline model to multiple target accents independently. To simplify the adaptation procedure, we explore adapting the baseline model to multiple target accents simultaneously with multi-accent mixed data. Thus, we propose using accent-specific top layer with gate mechanism (AST-G) to realize multi-accent adaptation. Compared with the baseline model and accent-specific adaptation, AST-G achieves 9.8% and 1.9% average relative WER reduction respectively. However, in real-world applications, we can't obtain the accent category label for inference in advance. Therefore, we apply using an accent classifier to predict the accent label. To jointly train the acoustic model and the accent classifier, we propose the multi-task learning with gate mechanism (MTL-G). As the accent label prediction could be inaccurate, it performs worse than the accent-specific adaptation. Yet, in comparison with the baseline model, MTL-G achieves 5.1% average relative WER reduction.