mlsanityData to 14 Oct 2026

LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR

arXiv 2610.16579 ↗First posted 12 Oct 2026cs.SD cs.LGcited by 0

On the map: Mixture-of-experts → Multimodal MoE models also fits: MoE large language models

Abstract (arXiv)

Code-switching (CS) speech, characterized by language alternation within a single utterance, is prevalent in multilingual communities and poses challenges to automatic speech recognition (ASR) due to rapid language transitions. We propose LLM-HB, a language-aware large language model-guided hotword biasing framework for code-switching ASR (CS-ASR). The framework incorporates a mixture-of-experts (MoE) adaptor and an auxiliary language prediction head to better capture and differentiate multilingual representations, while hotwords are injected through LLM-based prompting. Experiments on the ASRU2019 code-switching challenge test set demonstrate that LLM-HB achieves a 20.30% relative reduction in mixed error rate (MER) over the baseline, reaching 5.85% MER under a 15-distractor hotword setting. To the best of our knowledge, this is the first work to integrate LLM-guided biasing into code-switching ASR. We further release the extracted ASRU2019 hotword list to support future research.

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 24 of its 30 references that are in the map. First posted on arXiv 12 Oct 2026.

Builds on

24 of 30 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free6 Jan
  2. 2023BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition4 Oct

Other references · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2017Billion-scale similarity search with GPUscited by 2,497
  6. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  7. 2018AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scalecited by 128
  8. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 101
  9. 2020The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Resultscited by 44
  10. 2021The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoderscited by 32
  11. 2022Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarizationcited by 29
  12. 2022LAE: Language-Aware Encoder for Monolingual and Multilingual ASRcited by 22
10 more
  1. 2020CIF-based Collaborative Decoding for End-to-end Contextual Speech Recognitioncited by 21
  2. 2023Enhancing Code-switching Speech Recognition with Interactive Language Biasescited by 21
  3. 2024CTC-Assisted LLM-Based Contextual ASRcited by 19
  4. 2021Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorizationcited by 18
  5. 2023SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Abilitycited by 18
  6. 2023Code-Switching Text Generation and Injection in Mandarin-English ASRcited by 11
  7. 2025BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLMcited by 11
  8. 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 10
  9. 2025DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognitioncited by 2
  10. 2024XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognitioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
  2. 2026Are you speaking my languages? On spoken language adherence in multimodal LLMs
  3. 2024CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognition
  4. 2026NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  5. 2026Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling
  6. 2025SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs
  7. 2026Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
  8. 2024LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation