# Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition

arXiv: https://arxiv.org/abs/2602.01967 · HTML: https://mlsanity.com/paper/2602.01967/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 27 of 27)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://mlsanity.com/paper/2305.05084/) (2023)
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions](https://mlsanity.com/paper/2104.02724/) (2021)
- [SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts](https://mlsanity.com/paper/2105.03036/) (2021)
- [Personalizing ASR for Dysarthric and Accented Speech with Limited Data](https://mlsanity.com/paper/1907.13511/) (2019)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model](https://mlsanity.com/paper/1712.01541/) (2017)
- [Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech](https://mlsanity.com/paper/2109.06952/) (2021)
- [GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech](https://mlsanity.com/paper/2406.14875/) (2024)
- [Learning Fast Adaptation on Cross-Accented Speech Recognition](https://mlsanity.com/paper/2003.01901/) (2020)
- [Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities](https://mlsanity.com/paper/2207.11345/) (2022)
- [REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling](https://mlsanity.com/paper/2012.07353/) (2020)
- [Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning](https://mlsanity.com/paper/2103.05834/) (2021)
- [Mixture-of-Expert Conformer for Streaming Multilingual ASR](https://mlsanity.com/paper/2305.15663/) (2023)
- [Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings](https://mlsanity.com/paper/2110.03520/) (2021)
- [E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition](https://mlsanity.com/paper/2106.08211/) (2021)
- [Layer-wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition](https://mlsanity.com/paper/2204.09883/) (2022)
- [Accented Speech Recognition With Accent-specific Codebooks](https://mlsanity.com/paper/2310.15970/) (2023)
- [Improving Self-supervised Pre-training using Accent-Specific Codebooks](https://mlsanity.com/paper/2407.03734/) (2024)

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

- [CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition](https://mlsanity.com/paper/2610.19134/) (2026)

## Abstract (arXiv)

Accented speech remains a persistent challenge for automatic speech recognition (ASR), as most models are trained on data dominated by a few high-resource English varieties, leading to substantial performance degradation for other accents. Accent-agnostic approaches improve robustness yet struggle with heavily accented or unseen varieties, while accent-specific methods rely on limited and often noisy labels. We introduce Moe-Ctc, a Mixture-of-Experts architecture with intermediate CTC supervision that jointly promotes expert specialization and generalization. During training, accent-aware routing encourages experts to capture accent-specific patterns, which gradually transitions to label-free routing for inference. Each expert is equipped with its own CTC head to align routing with transcription quality, and a routing-augmented loss further stabilizes optimization. Experiments on the Mcv-Accent benchmark demonstrate consistent gains across both seen and unseen accents in low- and high-resource conditions, achieving up to 29.3% relative WER reduction over strong FastConformer baselines.