mlsanityData to 14 Oct 2026

Research on an improved Conformer end-to-end Speech Recognition Model with R-Drop Structure

arXiv 2306.08329 ↗First posted 14 Jun 2023cs.SD cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

To address the issue of poor generalization ability in end-to-end speech recognition models within deep learning, this study proposes a new Conformer-based speech recognition model called "Conformer-R" that incorporates the R-drop structure. This model combines the Conformer model, which has shown promising results in speech recognition, with the R-drop structure. By doing so, the model is able to effectively model both local and global speech information while also reducing overfitting through the use of the R-drop structure. This enhances the model's ability to generalize and improves overall recognition efficiency. The model was first pre-trained on the Aishell1 and Wenetspeech datasets for general domain adaptation, and subsequently fine-tuned on computer-related audio data. Comparison tests with classic models such as LAS and Wenet were performed on the same test set, demonstrating the Conformer-R model's ability to effectively improve generalization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 14 Jun 2023.

Builds on

26 of 36 references.

References · 26

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  2. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  3. 2016Language Modeling with Gated Convolutional Networkscited by 702
  4. 2015Listen, Attend and Spellcited by 543
  5. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  6. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 340
  7. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 235
  8. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 234
  9. 2021R-Drop: Regularized Dropout for Neural Networkscited by 202
  10. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 197
  11. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
  12. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
14 more
  1. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
  2. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 125
  3. 2020ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Contextcited by 97
  4. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 96
  5. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 91
  6. 2020Towards Fast and Accurate Streaming End-to-End ASRcited by 47
  7. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 47
  8. 2022Towards End-to-end Unsupervised Speech Recognitioncited by 45
  9. 2020Transformer-based Online CTC/attention End-to-End Speech Recognition Architecturecited by 28
  10. 2021End-to-End Multi-Channel Transformer for Speech Recognitioncited by 17
  11. 2018Advancing Acoustic-to-Word CTC Modelcited by 15
  12. 2022Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelscited by 14
  13. 2022InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASRcited by 5
  14. 2021SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognitioncited by 1

Built on by

Not cited yet.