mlsanityData to 7 Oct 2026

Jasper: An End-to-End Convolutional Neural Acoustic Model

arXiv 1904.03288 ↗First posted 5 Apr 2019eess.AS cs.CL cs.LGcited by 75

Not on the map. Why?

Abstract (arXiv)

In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data. Our model, Jasper, uses only 1D convolutions, batch normalization, ReLU, dropout, and residual connections. To improve training, we further introduce a new layer-wise optimizer called NovoGrad. Through experiments, we demonstrate that the proposed deep architecture performs as well or better than more complex choices. Our deepest Jasper variant uses 54 convolutional layers. With this architecture, we achieve 2.95% WER using a beam-search decoder with an external neural language model and 3.86% WER with a greedy decoder on LibriSpeech test-clean. We also report competitive results on the Wall Street Journal and the Hub5'00 conversational evaluation datasets.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 13; 2023: 17; 2024: 8; 2025: 4; 2026: 2.

75 papers.

Sort:

By area:

  1. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  3. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 90
  4. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 90
  5. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  6. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 77
  7. 2021VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversioncited by 63
  8. 2022Squeezeformer: An Efficient Transformer for Automatic Speech Recognitioncited by 50
  9. 2021One TTS Alignment To Rule Them Allcited by 47
  10. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  11. 2021Missing Value Imputation on Multidimensional Time Seriescited by 33
  12. 2021End-to-End Video-To-Speech Synthesis using Generative Adversarial Networkscited by 27
38 more
  1. 2022FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learningcited by 24
  2. 2023Audio-Visual Efficient Conformer for Robust Speech Recognitioncited by 22
  3. 2022A Survey of Multilingual Models for Automatic Speech Recognitioncited by 21
  4. 2023The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarioscited by 20
  5. 2021Integer-only Zero-shot Quantization for Efficient Speech Recognitioncited by 19
  6. 2021Pushing the Limits of Non-Autoregressive Speech Recognitioncited by 18
  7. 2023A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Taskscited by 13
  8. 2021FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularizationcited by 11
  9. 2021High Fidelity Speech Regeneration with Application to Speech Enhancementcited by 10
  10. 2021LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Readingcited by 10
  11. 2022ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognitioncited by 8
  12. 2024UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalizationcited by 8
  13. 2021Improving speech recognition models with small samples for air traffic control systemscited by 6
  14. 2021ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systemscited by 6
  15. 2022Easter2.0: Improving convolutional models for handwritten text recognitioncited by 6
  16. 2023Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Modelcited by 6
  17. 2021A Toolbox for Construction and Analysis of Speech Datasetscited by 5
  18. 2021Real World Robustness from Systematic Noisecited by 5
  19. 2022Generating gender-ambiguous voices for privacy-preserving speech recognitioncited by 5
  20. 2022Uconv-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognitioncited by 5
  21. 2021Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformerscited by 4
  22. 2022Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptationcited by 4
  23. 2021Do End-to-End Speech Recognition Models Care About Context?cited by 3
  24. 2021Dialectal Speech Recognition and Translation of Swiss German Speech to Standard German Text: Microsoft's Submission to SwissText 2021cited by 3
  25. 2021Discovery of Single Independent Latent Variablecited by 3
  26. 2022MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognitioncited by 3
  27. 2023PATCorrect: Non-autoregressive Phoneme-augmented Transformer for ASR Error Correctioncited by 3
  28. 2023Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognitioncited by 3
  29. 2021Error-driven Fixed-Budget ASR Personalization for Accented Speakerscited by 2
  30. 2021Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matricescited by 2
  31. 2021Deformable TDNN with adaptive receptive fields for speech recognitioncited by 2
  32. 2021Speech recognition for air traffic control via feature learning and end-to-end trainingcited by 2
  33. 2022Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognitioncited by 2
  34. 2024Non-autoregressive real-time Accent Conversion model with voice cloningcited by 2
  35. 2024OneEncoder: A Lightweight Framework for Progressive Alignment of Modalitiescited by 2
  36. 2024Training Large ASR Encoders with Differential Privacycited by 2
  37. 2025Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systemscited by 2
  38. 2021Efficient and Generic 1D Dilated Convolution Layer for Deep Learningcited by 1

50 most cited of 75 All 75 (JSON)