mlsanityData to 7 Oct 2026

Very Deep Convolutional Networks for End-to-End Speech Recognition

arXiv 1610.03022 ↗First posted 10 Oct 2016cs.CLcited by 34

Not on the map. Why?

Abstract (arXiv)

Sequence-to-sequence models have shown success in end-to-end speech recognition. However these models have only used shallow acoustic encoder networks. In our work, we successively train very deep convolutional networks to add more expressive power and better generalization for end-to-end ASR models. We apply network-in-network principles, batch normalization, residual connections and convolutional LSTMs to build very deep recurrent and convolutional structures. Our models exploit the spectral structure in the feature space and add computational depth without overfitting issues. We experiment with the WSJ ASR task and achieve 10.5% word error rate without any dictionary or language using a 15 layer deep network.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 12; 2023: 7; 2024: 2; 2025: 1.

34 papers.

Sort:

By area:

  1. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
  2. 2023End-to-End Speech Recognition: A Surveycited by 127
  3. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
  4. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  5. 2023Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfercited by 22
  6. 2021Pushing the Limits of Non-Autoregressive Speech Recognitioncited by 18
  7. 2021A Survey on Deep Reinforcement Learning for Audio-Based Applicationscited by 17
  8. 2021Homogeneous Architecture Augmentation for Neural Predictorcited by 14
  9. 2021Efficient Weight factorization for Multilingual Speech Recognitioncited by 12
  10. 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Modelscited by 9
  11. 2021Network In Graph Neural Networkcited by 8
  12. 2022ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognitioncited by 8
22 more
  1. 2022On Compressing Sequences for Self-Supervised Speech Modelscited by 7
  2. 2022Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processingcited by 7
  3. 2021Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognitioncited by 5
  4. 2021A Unified Speaker Adaptation Approach for ASRcited by 5
  5. 2023Sequential Estimation of Gaussian Process-based Deep State-Space Modelscited by 5
  6. 2021A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robotscited by 4
  7. 2022Insights on Neural Representations for End-to-End Speech Recognitioncited by 4
  8. 2021Do End-to-End Speech Recognition Models Care About Context?cited by 3
  9. 2022Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Surveycited by 3
  10. 2024Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNetcited by 3
  11. 2022Polyphonic pitch detection with convolutional recurrent neural networkscited by 1
  12. 2022A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognitioncited by 1
  13. 2022Prostate Cancer Malignancy Detection and localization from mpMRI using auto-Deep Learning: One Step Closer to Clinical Utilizationcited by 1
  14. 2022Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Lossescited by 1
  15. 2023TS-ENAS:Two-Stage Evolution for Cell-based Network Architecture Searchcited by 1
  16. 2023DDC-PIM: Efficient Algorithm/Architecture Co-design for Doubling Data Capacity of SRAM-based Processing-In-Memorycited by 1
  17. 2022Dynamic Latency for CTC-Based Streaming Automatic Speech Recognition With Emformercited by 0
  18. 2022DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognitioncited by 0
  19. 2022Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognitioncited by 0
  20. 2023Semi-supervised 3D Video Information Retrieval with Deep Neural Network and Bi-directional Dynamic-time Warping Algorithmcited by 0
  21. 2023Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Taskscited by 0
  22. 2025Unified Learnable 2D Convolutional Feature Extraction for ASRcited by 0