# Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM

arXiv: https://arxiv.org/abs/2409.15905 · HTML: https://mlsanity.com/paper/2409.15905/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs](https://mlsanity.com/paper/2407.04051/) (2024)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition](https://mlsanity.com/paper/2407.04675/) (2024)
- [The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results](https://mlsanity.com/paper/2007.05916/) (2020)
- [Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?](https://mlsanity.com/paper/2109.05422/) (2021)
- [Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets](https://mlsanity.com/paper/2405.02132/) (2024)
- [BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition](https://mlsanity.com/paper/2310.02629/) (2023)
- [SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR](https://mlsanity.com/paper/2406.18021/) (2024)
- [Enhancing Code-Switching Speech Recognition with LID-Based Collaborative Mixture of Experts Model](https://mlsanity.com/paper/2409.02050/) (2024)

## Built on by (most cited first, 9 of 9)

- [Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities](https://mlsanity.com/paper/2510.07037/) (2025)
- [Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs](https://mlsanity.com/paper/2605.23975/) (2026)
- [Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling](https://mlsanity.com/paper/2606.10439/) (2026)
- [A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario](https://mlsanity.com/paper/2412.00721/) (2024)
- [GLAD: Global-Local Aware Dynamic Mixture-of-Experts for Multi-Talker ASR](https://mlsanity.com/paper/2509.13093/) (2025)
- [A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR](https://mlsanity.com/paper/2601.00557/) (2026)
- [LLMs-Integrated Automatic Hate Speech Recognition Using Controllable Text Generation Models](https://mlsanity.com/paper/2601.04654/) (2026)
- [Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs](https://mlsanity.com/paper/2606.05846/) (2026)
- [Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition](https://mlsanity.com/paper/2609.02901/) (2026)

## Abstract (arXiv)

In this paper, we introduce a speech-conditioned Large Language Model (LLM) integrated with a Mixture of Experts (MoE) based connector to address the challenge of Code-Switching (CS) in Automatic Speech Recognition (ASR). Specifically, we propose an Insertion and Deletion of Interruption Token (IDIT) mechanism for better transfer text generation ability of LLM to speech recognition task. We also present a connecter with MoE architecture that manages multiple languages efficiently. To further enhance the collaboration of multiple experts and leverage the understanding capabilities of LLM, we propose a two-stage progressive training strategy: 1) The connector is unfrozen and trained with language-specialized experts to map speech representations to the text space. 2) The connector and LLM LoRA adaptor are trained with the proposed IDIT mechanism and all experts are activated to learn general representations. Experimental results demonstrate that our method significantly outperforms state-of-the-art models, including end-to-end and large-scale audio-language models.