mlsanityData to 14 Oct 2026

Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASR

arXiv 2606.10454 ↗First posted 9 Jun 2026eess.AS cs.SDcited by 1

On the map: Mixture-of-experts → Multimodal MoE models

Abstract (arXiv)

While Speech Large Language Models (Speech-LLMs) have achieved strong performance on adult Automatic Speech Recognition (ASR), their effectiveness on child speech remains under-explored, and single models often struggle to handle diverse adult and child age groups simultaneously. This paper proposes a Mixture-of-Experts (MoE) Speech-LLM for unified ASR across adult and child speech spanning diverse environments and age groups. The framework employs a Classifier-based Domain Router (C-DR) with a coarse-to-fine strategy and integrates both a Mixture-of-Projectors (MoP) and a Mixture-of-LoRAs (MoL) to model domain-specific variations. To address routing uncertainty near domain boundaries, an Entropy-Aware Routing (EAR) mechanism is introduced to dynamically incorporate a shared expert. Experiments on public child corpora demonstrate consistent improvements over baselines while preserving adult ASR performance. To our knowledge, this is the first work leveraging Speech-LLMs for unified, multi-domain ASR encompassing both children and adults.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts. Builds on 30 of its 33 references that are in the map. First posted on arXiv 9 Jun 2026.

Builds on

30 of 33 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition27 Jan
  2. 2026MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free6 Jan
  3. 2025Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach20 May
  4. 2024HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models30 Sep

Other references · 26

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  6. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  7. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  8. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  9. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 506
  10. 2022A Review of Sparse Expert Models in Deep Learningcited by 148
  11. 2023Prompting Large Language Models with Speech Recognition Abilitiescited by 140
  12. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 88
14 more
  1. 2024Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Modelscited by 29
  2. 2023My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speechcited by 28
  3. 2023Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASRcited by 23
  4. 2022DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASRcited by 21
  5. 2026EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoningcited by 15
  6. 2024Advancing Multi-talker ASR Performance with Large Language Modelscited by 10
  7. 2025Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audiocited by 10
  8. 2025Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnetcited by 6
  9. 2025Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognitioncited by 4
  10. 2025MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASRcited by 4
  11. 2026Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASRcited by 3
  12. 2025Enhancing Age-Related Robustness in Children Speaker Verificationcited by 2
  13. 2025Comparing Unsupervised and Supervised Semantic Speech Tokens: A Case Study of Child ASRcited by 2
  14. 2025An Age-Agnostic System for Robust Speaker Verificationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition
  2. 2026Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR
  3. 2026Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
  4. 2026NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  5. 2022Unified Modeling of Multi-Domain Multi-Device ASR Systems
  6. 2025GLAD: Global-Local Aware Dynamic Mixture-of-Experts for Multi-Talker ASR
  7. 2026Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling
  8. 2021SpeechMoE2: Mixture-of-Experts Model with Improved Routing