# E-Branchformer: Branchformer with Enhanced merging for speech recognition

arXiv: https://arxiv.org/abs/2210.00077 · HTML: https://mlsanity.com/paper/2210.00077/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 62 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 30 of 51)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [Pay Less Attention with Lightweight and Dynamic Convolutions](https://mlsanity.com/paper/1901.10430/) (2019)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [The Evolved Transformer](https://mlsanity.com/paper/1901.11117/) (2019)
- [DeepNet: Scaling Transformers to 1,000 Layers](https://mlsanity.com/paper/2203.00555/) (2022)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [Lite Transformer with Long-Short Range Attention](https://mlsanity.com/paper/2004.11886/) (2020)

## Built on by (most cited first, 30 of 92)

- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer](https://mlsanity.com/paper/2401.16658/) (2024)
- [Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks](https://mlsanity.com/paper/2309.07937/) (2023)
- [Towards Robust Speech Representation Learning for Thousands of Languages](https://mlsanity.com/paper/2407.00837/) (2024)
- [Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data](https://mlsanity.com/paper/2309.13876/) (2023)
- [Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study](https://mlsanity.com/paper/2309.15800/) (2023)
- [OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification](https://mlsanity.com/paper/2402.12654/) (2024)
- [ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets](https://mlsanity.com/paper/2406.08641/) (2024)
- [OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning](https://mlsanity.com/paper/2506.00338/) (2025)
- [Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute](https://mlsanity.com/paper/2306.06672/) (2023)
- [Exploring the Capability of Mamba in Speech Applications](https://mlsanity.com/paper/2406.16808/) (2024)
- [ZIPA: A family of efficient models for multilingual phone recognition](https://mlsanity.com/paper/2505.23170/) (2025)
- [CR-CTC: Consistency regularization on CTC for improved speech recognition](https://mlsanity.com/paper/2410.05101/) (2024)
- [A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks](https://mlsanity.com/paper/2305.11073/) (2023)
- [Multi-Head State Space Model for Speech Recognition](https://mlsanity.com/paper/2305.12498/) (2023)
- [SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding](https://mlsanity.com/paper/2307.07421/) (2023)
- [I3D: Transformer architectures with input-dependent dynamic depth for speech recognition](https://mlsanity.com/paper/2303.07624/) (2023)
- [ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit](https://mlsanity.com/paper/2304.04596/) (2023)
- [On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models](https://mlsanity.com/paper/2406.09282/) (2024)
- [DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding](https://mlsanity.com/paper/2406.09345/) (2024)
- [MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition](https://mlsanity.com/paper/2401.03424/) (2024)
- [Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning](https://mlsanity.com/paper/2309.15317/) (2023)
- [Ternary Spike-based Neuromorphic Signal Processing System](https://mlsanity.com/paper/2407.05310/) (2024)
- [Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages](https://mlsanity.com/paper/2503.20212/) (2025)
- [SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision](https://mlsanity.com/paper/2512.20308/) (2025)
- [Neural Blind Source Separation and Diarization for Distant Speech Recognition](https://mlsanity.com/paper/2406.08396/) (2024)
- [Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet](https://mlsanity.com/paper/2508.16576/) (2025)
- [HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition](https://mlsanity.com/paper/2305.18281/) (2023)
- [Revisiting ASR Error Correction with Specialized Models](https://mlsanity.com/paper/2405.15216/) (2024)

## Abstract (arXiv)

Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR). Several other studies have explored integrating convolution and self-attention but they have not managed to match Conformer's performance. The recently introduced Branchformer achieves comparable performance to Conformer by using dedicated branches of convolution and self-attention and merging local and global context from each branch. In this paper, we propose E-Branchformer, which enhances Branchformer by applying an effective merging method and stacking additional point-wise modules. E-Branchformer sets new state-of-the-art word error rates (WERs) 1.81% and 3.65% on LibriSpeech test-clean and test-other sets without using any external training data.