mlsanityData to 7 Oct 2026

Speech Recognition with Deep Recurrent Neural Networks

arXiv 1303.5778 ↗First posted 22 Mar 2013cs.NE cs.CLcited by 666

Not on the map. Why?

Abstract (arXiv)

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is unknown. The combination of these methods with the Long Short-term Memory RNN architecture has proved particularly fruitful, delivering state-of-the-art results in cursive handwriting recognition. However RNN performance in speech recognition has so far been disappointing, with better results returned by deep feedforward networks. This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs. When trained end-to-end with suitable regularisation, we find that deep Long Short-term Memory RNNs achieve a test set error of 17.7% on the TIMIT phoneme recognition benchmark, which to our knowledge is the best recorded score.

Key facts. Cited by 666 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Mar 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 0; 2021: 207; 2022: 158; 2023: 130; 2024: 83; 2025: 58; 2026: 27.

666 papers.

Sort:

By area:

  1. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  2. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  3. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  4. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  5. 2021Towards Causal Representation Learningcited by 207
  6. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 189
  7. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  8. 2021Activation Functions in Deep Learning: A Comprehensive Survey and Benchmarkcited by 153
  9. 2022Towards Understanding Sharpness-Aware Minimizationcited by 145
  10. 2022Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognitioncited by 139
  11. 2021Hyperbolic Deep Neural Networks: A Surveycited by 138
  12. 2023End-to-End Speech Recognition: A Surveycited by 127
38 more
  1. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  2. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 117
  3. 2021Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approachcited by 105
  4. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 92
  5. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 86
  6. 2023Machine Unlearning: Solutions and Challengescited by 85
  7. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  8. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  9. 2021Visual Alignment Constraint for Continuous Sign Language Recognitioncited by 79
  10. 2022Knowledge Tracing: A Surveycited by 76
  11. 2021Practical Blind Membership Inference Attack via Differential Comparisonscited by 73
  12. 2023Calibration in Deep Learning: A Survey of the State-of-the-Artcited by 72
  13. 2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
  14. 2023Scallop: A Language for Neurosymbolic Programmingcited by 63
  15. 2024YODAS: Youtube-Oriented Dataset for Audio and Speechcited by 56
  16. 2021SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalizationcited by 50
  17. 2021Poison Ink: Robust and Invisible Backdoor Attackcited by 50
  18. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 49
  19. 2021Deep Model Intellectual Property Protection via Deep Watermarkingcited by 47
  20. 2022FiNER: Financial Numeric Entity Recognition for XBRL Taggingcited by 47
  21. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  22. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 46
  23. 2022Deep Nonparametric Estimation of Operators between Infinite Dimensional Spacescited by 45
  24. 2022BadDet: Backdoor Attacks on Object Detectioncited by 45
  25. 2023An Over-parameterized Exponential Regressioncited by 45
  26. 2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
  27. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  28. 2024WirelessLLM: Empowering Large Language Models Towards Wireless Intelligencecited by 43
  29. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  30. 2023Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoringcited by 42
  31. 2023Maintaining Plasticity in Deep Continual Learningcited by 42
  32. 2022Transformers in Medical Image Analysis: A Reviewcited by 41
  33. 2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
  34. 2022The Unreasonable Effectiveness of Deep Evidential Regressioncited by 40
  35. 2021An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognitioncited by 39
  36. 2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 38
  37. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  38. 2021Momentum Pseudo-Labeling for Semi-Supervised Speech Recognitioncited by 37

50 most cited of 666 All 666 (JSON)