# Layer-wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition

arXiv: https://arxiv.org/abs/2204.09883 · HTML: https://mlsanity.com/paper/2204.09883/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2022.

## Built on by (most cited first, 12 of 12)

- [Improving the Training Recipe for a Robust Conformer-based Hybrid Model](https://mlsanity.com/paper/2206.12955/) (2022)
- [Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition](https://mlsanity.com/paper/2505.20006/) (2025)
- [Exploration of Adapter for Noise Robust Automatic Speech Recognition](https://mlsanity.com/paper/2402.18275/) (2024)
- [Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition](https://mlsanity.com/paper/2306.11309/) (2023)
- [ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks](https://mlsanity.com/paper/2407.21066/) (2024)
- [Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder](https://mlsanity.com/paper/2211.03316/) (2022)
- [Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition](https://mlsanity.com/paper/2407.03026/) (2024)
- [Improving Self-supervised Pre-training using Accent-Specific Codebooks](https://mlsanity.com/paper/2407.03734/) (2024)
- [Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition](https://mlsanity.com/paper/2602.01967/) (2026)
- [Cascaded Multi-task Adaptive Learning Based on Neural Architecture Search](https://mlsanity.com/paper/2310.17664/) (2023)
- [Adapter-based Approaches to Knowledge-enhanced Language Models -- A Survey](https://mlsanity.com/paper/2411.16403/) (2024)
- [Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy](https://mlsanity.com/paper/2604.01705/) (2026)

## Abstract (arXiv)

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle unseen accents. Furthermore, simply concatenating accent embeddings does not make good use of accent knowledge, which has limited improvements. In this work, we aim to tackle these problems with a novel layer-wise adaptation structure injected into the E2E ASR model encoder. The adapter layer encodes an arbitrary accent in the accent space and assists the ASR model in recognizing accented speech. Given an utterance, the adaptation structure extracts the corresponding accent information and transforms the input acoustic feature into an accent-related feature through the linear combination of all accent bases. We further explore the injection position of the adaptation layer, the number of accent bases, and different types of accent bases to achieve better accent adaptation. Experimental results show that the proposed adaptation structure brings 12% and 10% relative word error rate~(WER) reduction on the AESRC2020 accent dataset and the Librispeech dataset, respectively, compared to the baseline.