# Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition

arXiv: https://arxiv.org/abs/2209.08326 · HTML: https://mlsanity.com/paper/2209.08326/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 17 Sep 2022.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View](https://mlsanity.com/paper/1906.02762/) (2019)
- [FastMoE: A Fast Mixture-of-Expert Training System](https://mlsanity.com/paper/2103.13262/) (2021)
- [Go Wider Instead of Deeper](https://mlsanity.com/paper/2107.11817/) (2021)
- [SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts](https://mlsanity.com/paper/2105.03036/) (2021)
- [Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation](https://mlsanity.com/paper/1910.13296/) (2019)
- [Non-Autoregressive ASR with Self-Conditioned Folded Encoders](https://mlsanity.com/paper/2202.08474/) (2022)

## Built on by (most cited first, 3 of 3)

- [Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves](https://mlsanity.com/paper/2601.21582/) (2026)
- [Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing](https://mlsanity.com/paper/2407.18581/) (2024)
- [On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition](https://mlsanity.com/paper/2505.22072/) (2025)

## Abstract (arXiv)

While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the parameters of the model. However, the inevitable loss of capacity harms the model performance. To address this issue, this paper proposes a parameter-efficient conformer via sharing sparsely-gated experts. Specifically, we use sparsely-gated mixture-of-experts (MoE) to extend the capacity of a conformer block without increasing computation. Then, the parameters of the grouped conformer blocks are shared so that the number of parameters is reduced. Next, to ensure the shared blocks with the flexibility of adapting representations at different levels, we design the MoE routers and normalization individually. Moreover, we use knowledge distillation to further improve the performance. Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.