mlsanityData to 14 Oct 2026

Improved training of end-to-end attention models for speech recognition

arXiv 1805.03294 ↗First posted 8 May 2018cs.CL cs.LG stat.MLcited by 36

Not on the map. Why?

Abstract (arXiv)

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h tasks. In particular, we report the state-of-the-art word error rates (WER) of 3.54% on the dev-clean and 3.82% on the test-clean evaluation subsets of LibriSpeech. We introduce a new pretraining scheme by starting with a high time reduction factor and lowering it during training, which is crucial both for convergence and final performance. In some experiments, we also use an auxiliary CTC loss function to help the convergence. In addition, we train long short-term memory (LSTM) language models on subword units. By shallow fusion, we report up to 27% relative improvements in WER over the attention baseline without a language model.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 10; 2023: 7; 2024: 3; 2025: 2; 2026: 1.

36 papers.

Sort:

By area:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
  2. 2023End-to-End Speech Recognition: A Surveycited by 129
  3. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 92
  4. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 91
  5. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 51
  6. 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 42
  7. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  8. 2021Librispeech Transducer Model with Internal Language Model Prior Correctioncited by 26
  9. 2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
  10. 2022Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilitiescited by 16
  11. 2023A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Taskscited by 14
  12. 2021Arabic Speech Recognition by End-to-End, Modular Systems and Humancited by 12
24 more
  1. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  2. 2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architecturescited by 8
  3. 2022Minimum Latency Training of Sequence Transducers for Streaming End-to-End Speech Recognitioncited by 8
  4. 2024MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decodercited by 7
  5. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  6. 2021Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognitioncited by 5
  7. 2021A study of latent monotonic attention variantscited by 5
  8. 2021Equivalence of Segmental and Neural Transducer Modeling: A Proof of Conceptcited by 5
  9. 2022A Likelihood Ratio based Domain Adaptation Method for E2E Modelscited by 5
  10. 2021Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognitioncited by 4
  11. 2022Two-Pass End-to-End ASR Model Compressioncited by 4
  12. 2022Monotonic segmental attention for automatic speech recognitioncited by 4
  13. 2023On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognitioncited by 4
  14. 2024Exploring the Benefits of Tokenization of Discrete Acoustic Unitscited by 4
  15. 2025Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognitioncited by 4
  16. 2021Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscriptscited by 3
  17. 2023UML: A Universal Monolingual Output Layer for Multilingual ASRcited by 3
  18. 2022Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothingcited by 2
  19. 2022Comparison and Analysis of New Curriculum Criteria for End-to-End ASRcited by 2
  20. 2024The Conformer Encoder May Reverse the Time Dimensioncited by 2
  21. 2021HMM-Free Encoder Pre-Training for Streaming RNN Transducercited by 1
  22. 2025Micromobility Flow Prediction: A Bike Sharing Station-level Study via Multi-level Spatial-Temporal Attention Neural Networkcited by 1
  23. 2026Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMscited by 1
  24. 2023Exploring Turkish Speech Recognition via Hybrid CTC/Attention Architecture and Multi-feature Fusion Networkcited by 0