# Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing

arXiv: https://arxiv.org/abs/2407.18581 · HTML: https://mlsanity.com/paper/2407.18581/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [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)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters](https://mlsanity.com/paper/2007.03001/) (2020)
- [WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2203.15455/) (2022)
- [The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results](https://mlsanity.com/paper/2007.05916/) (2020)
- [MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition](https://mlsanity.com/paper/2302.13750/) (2023)
- [Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization](https://mlsanity.com/paper/2210.14567/) (2022)
- [SpeechMoE2: Mixture-of-Experts Model with Improved Routing](https://mlsanity.com/paper/2111.11831/) (2021)
- [Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition](https://mlsanity.com/paper/2307.05956/) (2023)
- [LAE: Language-Aware Encoder for Monolingual and Multilingual ASR](https://mlsanity.com/paper/2206.02093/) (2022)
- [Enhancing Code-switching Speech Recognition with Interactive Language Biases](https://mlsanity.com/paper/2309.16953/) (2023)
- [Language-specific Characteristic Assistance for Code-switching Speech Recognition](https://mlsanity.com/paper/2206.14580/) (2022)
- [Mixture-of-Expert Conformer for Streaming Multilingual ASR](https://mlsanity.com/paper/2305.15663/) (2023)
- [Towards Zero-Shot Code-Switched Speech Recognition](https://mlsanity.com/paper/2211.01458/) (2022)
- [BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition](https://mlsanity.com/paper/2310.02629/) (2023)
- [An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging Encoder Disentanglement](https://mlsanity.com/paper/2402.17189/) (2024)
- [U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF](https://mlsanity.com/paper/2404.16407/) (2024)
- [Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition](https://mlsanity.com/paper/2209.08326/) (2022)

## Built on by (most cited first, 2 of 2)

- [Mixture of Experts (MoE): A Big Data Perspective](https://mlsanity.com/paper/2501.16352/) (2025)
- [MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition](https://mlsanity.com/paper/2607.24030/) (2026)

## Abstract (arXiv)

The Mixture of Experts (MoE) model is a promising approach for handling code-switching speech recognition (CS-ASR) tasks. However, the existing CS-ASR work on MoE has yet to leverage the advantages of MoE's parameter scaling ability fully. This work proposes DLG-MoE, a Dynamic Language Group-based MoE, which can effectively handle the CS-ASR task and leverage the advantages of parameter scaling. DLG-MoE operates based on a hierarchical routing mechanism. First, the language router explicitly models the language attribute and dispatches the representations to the corresponding language expert groups. Subsequently, the unsupervised router within each language group implicitly models attributes beyond language and coordinates expert routing and collaboration. DLG-MoE outperforms the existing MoE methods on CS-ASR tasks while demonstrating great flexibility. It supports different top-k inference and streaming capabilities and can also prune the model parameters flexibly to obtain a monolingual sub-model. The code has been released.