mlsanityData to 7 Oct 2026

End-to-End Attention-based Large Vocabulary Speech Recognition

arXiv 1508.04395 ↗First posted 18 Aug 2015cs.CL cs.AI cs.LGcited by 148

Not on the map. Why?

Abstract (arXiv)

Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the acoustic modelling, language modelling and sequence decoding. We investigate a more direct approach in which the HMM is replaced with a Recurrent Neural Network (RNN) that performs sequence prediction directly at the character level. Alignment between the input features and the desired character sequence is learned automatically by an attention mechanism built into the RNN. For each predicted character, the attention mechanism scans the input sequence and chooses relevant frames. We propose two methods to speed up this operation: limiting the scan to a subset of most promising frames and pooling over time the information contained in neighboring frames, thereby reducing source sequence length. Integrating an n-gram language model into the decoding process yields recognition accuracies similar to other HMM-free RNN-based approaches.

Key facts. Cited by 148 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Aug 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 52; 2022: 46; 2023: 28; 2024: 12; 2025: 7; 2026: 3.

148 papers.

Sort:

By area:

  1. 2022Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Predictioncited by 277
  2. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  3. 2023End-to-End Speech Recognition: A Surveycited by 127
  4. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
  5. 2021Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictionscited by 61
  6. 2022UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Unitscited by 60
  7. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  8. 2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
  9. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  10. 2021Tied & Reduced RNN-T Decodercited by 35
  11. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
  12. 2021Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformercited by 34
38 more
  1. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  2. 2022Attention as a Guide for Simultaneous Speech Translationcited by 32
  3. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
  4. 2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
  5. 2021Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separationcited by 27
  6. 2023Pre-training for Speech Translation: CTC Meets Optimal Transportcited by 25
  7. 2023AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representationscited by 24
  8. 2021Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learningcited by 20
  9. 2021An evaluation of word-level confidence estimation for end-to-end automatic speech recognitioncited by 18
  10. 2021End-to-End Spoken Language Understanding for Generalized Voice Assistantscited by 17
  11. 2021On Language Model Integration for RNN Transducer based Speech Recognitioncited by 17
  12. 2022Accelerating RNN-T Training and Inference Using CTC guidancecited by 17
  13. 2022Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilitiescited by 16
  14. 2024Attention layers provably solve single-location regressioncited by 15
  15. 2022Efficient Training of Neural Transducer for Speech Recognitioncited by 14
  16. 2023An End-to-End Multi-Task Learning Model for Image-based Table Recognitioncited by 14
  17. 2021Domain-aware Neural Language Models for Speech Recognitioncited by 13
  18. 2022Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASRcited by 13
  19. 2021Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillationcited by 12
  20. 2021Efficient Weight factorization for Multilingual Speech Recognitioncited by 12
  21. 2022Minimal Width for Universal Property of Deep RNNcited by 12
  22. 2021Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognitioncited by 11
  23. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  24. 2021End2End Acoustic to Semantic Transductioncited by 10
  25. 2022Adaptive multilingual speech recognition with pretrained modelscited by 9
  26. 2022LegoNN: Building Modular Encoder-Decoder Modelscited by 9
  27. 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Modelscited by 9
  28. 2023Boosting Crop Classification by Hierarchically Fusing Satellite, Rotational, and Contextual Datacited by 8
  29. 2021Language model fusion for streaming end to end speech recognitioncited by 7
  30. 2021On lattice-free boosted MMI training of HMM and CTC-based full-context ASR modelscited by 7
  31. 2022USTED: Improving ASR with a Unified Speech and Text Encoder-Decodercited by 7
  32. 2022End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention systemcited by 7
  33. 2022Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognitioncited by 7
  34. 2022End-to-end Speech-to-Punctuated-Text Recognitioncited by 7
  35. 2022On Compressing Sequences for Self-Supervised Speech Modelscited by 7
  36. 2022Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processingcited by 7
  37. 2021Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognitioncited by 6
  38. 2021Boosted Embeddings for Time Series Forecastingcited by 6

50 most cited of 148 All 148 (JSON)