# A Conformer Based Acoustic Model for Robust Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2203.00725 · HTML: https://mlsanity.com/paper/2203.00725/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer](https://mlsanity.com/paper/1801.00841/) (2018)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [Continuous Speech Separation with Conformer](https://mlsanity.com/paper/2008.05773/) (2020)
- [Far-Field Automatic Speech Recognition](https://mlsanity.com/paper/2009.09395/) (2020)
- [Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline](https://mlsanity.com/paper/1803.10109/) (2018)
- [Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition](https://mlsanity.com/paper/2110.04934/) (2021)
- [The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans](https://mlsanity.com/paper/2012.13006/) (2020)
- [Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction](https://mlsanity.com/paper/2110.15430/) (2021)
- [End-to-end Neural Diarization: From Transformer to Conformer](https://mlsanity.com/paper/2106.07167/) (2021)
- [Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora](https://mlsanity.com/paper/2109.11086/) (2021)

## Built on by (most cited first, 6 of 6)

- [End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation](https://mlsanity.com/paper/2204.00540/) (2022)
- [Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction](https://mlsanity.com/paper/2306.09313/) (2023)
- [Improving the Training Recipe for a Robust Conformer-based Hybrid Model](https://mlsanity.com/paper/2206.12955/) (2022)
- [AG-LSEC: Audio Grounded Lexical Speaker Error Correction](https://mlsanity.com/paper/2406.17266/) (2024)
- [Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring](https://mlsanity.com/paper/2310.09680/) (2023)
- [SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models](https://mlsanity.com/paper/2501.08421/) (2025)

## Abstract (arXiv)

This study addresses robust automatic speech recognition (ASR) by introducing a Conformer-based acoustic model. The proposed model builds on the wide residual bi-directional long short-term memory network (WRBN) with utterance-wise dropout and iterative speaker adaptation, but employs a Conformer encoder instead of the recurrent network. The Conformer encoder uses a convolution-augmented attention mechanism for acoustic modeling. The proposed system is evaluated on the monaural ASR task of the CHiME-4 corpus. Coupled with utterance-wise normalization and speaker adaptation, our model achieves 6.25% word error rate, which outperforms WRBN by 8.4% relatively. In addition, the proposed Conformer-based model is 18.3% smaller in model size and reduces total training time by 79.6%.