# On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition

arXiv: https://arxiv.org/abs/2505.22072 · HTML: https://mlsanity.com/paper/2505.22072/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 34 of its 43 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [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)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024)
- [SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts](https://mlsanity.com/paper/2105.03036/) (2021)
- [Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition](https://mlsanity.com/paper/2202.03218/) (2022)
- [MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition](https://mlsanity.com/paper/2302.13750/) (2023)
- [Investigation of Data Augmentation Techniques for Disordered Speech Recognition](https://mlsanity.com/paper/2201.05562/) (2022)
- [Exploring Efficient-tuning Methods in Self-supervised Speech Models](https://mlsanity.com/paper/2210.06175/) (2022)
- [Speaker adaptation for Wav2vec2 based dysarthric ASR](https://mlsanity.com/paper/2204.00770/) (2022)
- [Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2202.10290/) (2022)
- [Recent Progress in the CUHK Dysarthric Speech Recognition System](https://mlsanity.com/paper/2201.05845/) (2022)
- [Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition](https://mlsanity.com/paper/2204.01670/) (2022)
- [Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation](https://mlsanity.com/paper/2401.00662/) (2024)
- [Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition](https://mlsanity.com/paper/2203.15431/) (2022)
- [Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2302.14564/) (2023)
- [CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models](https://mlsanity.com/paper/2212.01282/) (2022)
- [Efficient Domain Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2302.01496/) (2023)
- [Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition](https://mlsanity.com/paper/2203.10274/) (2022)
- [BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition](https://mlsanity.com/paper/2310.02629/) (2023)
- [Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2407.13782/) (2024)
- [Use of Speech Impairment Severity for Dysarthric Speech Recognition](https://mlsanity.com/paper/2305.10659/) (2023)
- [Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition](https://mlsanity.com/paper/2206.07327/) (2022)
- [DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model](https://mlsanity.com/paper/2306.10588/) (2023)
- [Aphasic Speech Recognition using a Mixture of Speech Intelligibility Experts](https://mlsanity.com/paper/2008.10788/) (2020)
- [Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition](https://mlsanity.com/paper/2406.09873/) (2024)

## Abstract (arXiv)

This paper proposes a novel MoE-based speaker adaptation framework for foundation models based dysarthric speech recognition. This approach enables zero-shot adaptation and real-time processing while incorporating domain knowledge. Speech impairment severity and gender conditioned adapter experts are dynamically combined using on-the-fly predicted speaker-dependent routing parameters. KL-divergence is used to further enforce diversity among experts and their generalization to unseen speakers. Experimental results on the UASpeech corpus suggest that on-the-fly MoE-based adaptation produces statistically significant WER reductions of up to 1.34% absolute (6.36% relative) over the unadapted baseline HuBERT/WavLM models. Consistent WER reductions of up to 2.55% absolute (11.44% relative) and RTF speedups of up to 7 times are obtained over batch-mode adaptation across varying speaker-level data quantities. The lowest published WER of 16.35% (46.77% on very low intelligibility) is obtained.