mlsanityData to 7 Oct 2026

A Conformer Based Acoustic Model for Robust Automatic Speech Recognition

arXiv 2203.00725 ↗First posted 1 Mar 2022cs.SD cs.AI cs.CLcited by 6

Not on the map. Why?

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%.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 1 Mar 2022.

Builds on

21 of 37 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Wide Residual Networkscited by 3,057
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2020On Layer Normalization in the Transformer Architecturecited by 906
  5. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  6. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  7. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  8. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 232
  9. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 210
  10. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
  11. 2020CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordingscited by 129
  12. 2018Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducercited by 95
9 more
  1. 2018The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselinescited by 90
  2. 2020Continuous Speech Separation with Conformercited by 36
  3. 2020Far-Field Automatic Speech Recognitioncited by 32
  4. 2018Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baselinecited by 17
  5. 2021Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognitioncited by 15
  6. 2020The 2020 ESPnet update: new features, broadened applications, performance improvements, and future planscited by 14
  7. 2021End-to-end Neural Diarization: From Transformer to Conformercited by 12
  8. 2021Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstructioncited by 12
  9. 2021Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corporacited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 1; 2025: 1.

6 papers.

  1. 2022End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representationcited by 17
  2. 2023Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correctioncited by 14
  3. 2022Improving the Training Recipe for a Robust Conformer-based Hybrid Modelcited by 9
  4. 2024AG-LSEC: Audio Grounded Lexical Speaker Error Correctioncited by 3
  5. 2023Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoringcited by 1
  6. 2025SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Modelscited by 1