mlsanityData to 7 Oct 2026

MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition

arXiv 2102.12664 ↗First posted 25 Feb 2021cs.CL cs.SD eess.AScited by 38

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features (e.g., mel-spectrograms or MFCC) as the input, and recognizing both text sequences, where the two recognition losses use the same combination weight. We apply MixSpeech on two popular end-to-end speech recognition models including LAS (Listen, Attend and Spell) and Transformer, and conduct experiments on several low-resource datasets including TIMIT, WSJ, and HKUST. Experimental results show that MixSpeech achieves better accuracy than the baseline models without data augmentation, and outperforms a strong data augmentation method SpecAugment on these recognition tasks. Specifically, MixSpeech outperforms SpecAugment with a relative PER improvement of 10.6% on TIMIT dataset, and achieves a strong WER of 4.7% on WSJ dataset.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 12 of its 29 references that are in the map. First posted on arXiv 25 Feb 2021.

Builds on

12 of 29 references.

References · 12

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  5. 2015Listen, Attend and Spellcited by 542
  6. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
  7. 2019Augmenting Data with Mixup for Sentence Classification: An Empirical Studycited by 125
  8. 2019Transformers with convolutional context for ASRcited by 44
  9. 2020LRSpeech: Extremely Low-Resource Speech Synthesis and Recognitioncited by 43
  10. 2019Almost Unsupervised Text to Speech and Automatic Speech Recognitioncited by 41
  11. 2019Semantic Mask for Transformer based End-to-End Speech Recognitioncited by 18
  12. 2018Deep Convolutional Neural Network with Mixup for Environmental Sound Classificationcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 8; 2023: 17; 2024: 6; 2025: 4; 2026: 1.

38 papers.

Sort:

  1. 2023End-to-End Speech Recognition: A Surveycited by 127
  2. 2022STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translationcited by 57
  3. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  4. 2022A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspectivecited by 27
  5. 2022M3ST: Mix at Three Levels for Speech Translationcited by 21
  6. 2023Cross-modality Data Augmentation for End-to-End Sign Language Translationcited by 16
  7. 2022CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representationscited by 11
  8. 2022Exploring Temporally Dynamic Data Augmentation for Video Recognitioncited by 9
  9. 2024Posterior Uncertainty Quantification in Neural Networks using Data Augmentationcited by 9
  10. 2023Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixupcited by 8
  11. 2023R-Mixup: Riemannian Mixup for Biological Networkscited by 8
  12. 2021SpliceOut: A Simple and Efficient Audio Augmentation Methodcited by 7
26 more
  1. 2022Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translationcited by 6
  2. 2023Advancing Stuttering Detection via Data Augmentation, Class-Balanced Loss and Multi-Contextual Deep Learningcited by 5
  3. 2023Tailoring Mixup to Data for Calibrationcited by 5
  4. 2024Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognitioncited by 5
  5. 2023CoSDA: Continual Source-Free Domain Adaptationcited by 4
  6. 2023Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speechcited by 4
  7. 2024IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighborscited by 4
  8. 2025Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languagescited by 4
  9. 2021PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognitioncited by 3
  10. 2022SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategycited by 3
  11. 2023Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognitioncited by 3
  12. 2023Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Datacited by 3
  13. 2023Hate Speech Detection in Limited Data Contexts using Synthetic Data Generationcited by 3
  14. 2023Matching-based Term Semantics Pre-training for Spoken Patient Query Understandingcited by 2
  15. 2023Language-universal phonetic encoder for low-resource speech recognitioncited by 2
  16. 2023MixRep: Hidden Representation Mixup for Low-Resource Speech Recognitioncited by 2
  17. 2025NeuroAMP: A Novel End-to-end General Purpose Deep Neural Amplifier for Personalized Hearing Aidscited by 2
  18. 2026Scaling Ambiguity: Augmenting Human Annotation in Speech Emotion Recognition with Audio-Language Modelscited by 2
  19. 2023PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognitioncited by 1
  20. 2024Text2Data: Low-Resource Data Generation with Textual Controlcited by 1
  21. 2025Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Predictioncited by 1
  22. 2025Data Augmentation and Hyperparameter Tuning for Low-Resource MFAcited by 1
  23. 2023Improving Spoken Language Identification with Map-Mixcited by 0
  24. 2023Creating Spoken Dialog Systems in Ultra-Low Resourced Settingscited by 0
  25. 2024Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASRcited by 0
  26. 2024Revisiting Interpolation Augmentation for Speech-to-Text Generationcited by 0