mlsanityData to 19 Oct 2026

Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition

arXiv 2204.04284 ↗First posted 8 Apr 2022eess.AS cs.SDcited by 1

On the map: Speech and audio language models → Multilingual and low-resource ASR

Abstract (arXiv)

End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space through data augmentation. Meanwhile, human auditory inspired front-ends have also demonstrated improvement for automatic speech recognisers. In this work, a well-verified auditory-based model, which can simulate various hearing abilities, is investigated for the purpose of data augmentation for end-to-end speech recognition. By introducing the auditory model into the data augmentation process, end-to-end systems are encouraged to ignore variation from the signal that cannot be heard and thereby focus on robust features for speech recognition. Two mechanisms in the auditory model, spectral smearing and loudness recruitment, are studied on the LibriSpeech dataset with a transformer-based end-to-end model. The results show that the proposed augmentation methods can bring statistically significant improvement on the performance of the state-of-the-art SpecAugment.

Key facts. Cited by 1 paper in the map (data through 19 Oct 2026). Placed in Multilingual and low-resource ASR, one of 11 directions in Speech and audio language models. Builds on 12 of its 38 references that are in the map. First posted on arXiv 8 Apr 2022.

Builds on

12 of 38 references.

References · 12

  1. 2017Attention Is All You Needcited by 61,180
  2. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,636
  3. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 532
  4. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 320
  5. 2018The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselinescited by 154
  6. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 147
  7. 2020ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Contextcited by 120
  8. 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 80
  9. 2020Data Augmenting Contrastive Learning of Speech Representations in the Time Domaincited by 67
  10. 2020Small energy masking for improved neural network training for end-to-end speech recognitioncited by 4
  11. 2021Optimising Hearing Aid Fittings for Speech in Noise with a Differentiable Hearing Loss Modelcited by 2
  12. 2017On the Relevance of Auditory-Based Gabor Features for Deep Learning in Automatic Speech Recognitioncited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022A Policy-based Approach to the SpecAugment Method for Low Resource E2E ASRcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2021Data Augmentation Methods for End-to-end Speech Recognition on Distant-Talk Scenarios
  2. 2021SpliceOut: A Simple and Efficient Audio Augmentation Method
  3. 2023Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation
  4. 2023Pre-training End-to-end ASR Models with Augmented Speech Samples Queried by Text
  5. 2023A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit
  6. 2021An Investigation of End-to-End Models for Robust Speech Recognition
  7. 2022Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation
  8. 2022Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech