mlsanityData to 7 Oct 2026

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

arXiv 1904.08779 ↗First posted 18 Apr 2019eess.AS cs.CL cs.LGcited by 1,355

Not on the map. Why?

Abstract (arXiv)

We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5'00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.

Key facts. Cited by 1,355 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 326; 2022: 341; 2023: 249; 2024: 174; 2025: 158; 2026: 107.

1,355 papers.

Sort:

By area:

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  3. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  4. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  5. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  6. 2021AST: Audio Spectrogram Transformercited by 634
  7. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
  8. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  9. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  10. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 378
  11. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  12. 2021Attention Bottlenecks for Multimodal Fusioncited by 361
38 more
  1. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 340
  2. 2022Masked Autoencoders that Listencited by 271
  3. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
  4. 2021Efficient Training of Audio Transformers with Patchoutcited by 222
  5. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 194
  6. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 189
  7. 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 174
  8. 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 166
  9. 2023Stabilizing Transformer Training by Preventing Attention Entropy Collapsecited by 154
  10. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
  11. 2021Direct speech-to-speech translation with discrete unitscited by 148
  12. 2021End-to-end Audio-visual Speech Recognition with Conformerscited by 147
  13. 2021Unsupervised Speech Recognitioncited by 147
  14. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  15. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  16. 2023End-to-End Speech Recognition: A Surveycited by 127
  17. 2023X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languagescited by 127
  18. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  19. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
  20. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  21. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
  22. 2022Visual Speech Recognition for Multiple Languages in the Wildcited by 94
  23. 2023Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMcited by 92
  24. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 90
  25. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 90
  26. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  27. 2023VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translationcited by 87
  28. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  29. 2021PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregationcited by 81
  30. 2022MAESTRO: Matched Speech Text Representations through Modality Matchingcited by 79
  31. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 77
  32. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  33. 2021Translatotron 2: High-quality direct speech-to-speech translation with voice preservationcited by 69
  34. 2021WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesiscited by 65
  35. 2022Unified Speech-Text Pre-training for Speech Translation and Recognitioncited by 64
  36. 2022Vocalsound: A Dataset for Improving Human Vocal Sounds Recognitioncited by 62
  37. 2021Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictionscited by 61
  38. 2021Scaling End-to-End Models for Large-Scale Multilingual ASRcited by 61

50 most cited of 1,355 All 1,355 (JSON)