mlsanityData to 7 Oct 2026

Exploring Neural Transducers for End-to-End Speech Recognition

arXiv 1707.07413 ↗First posted 24 Jul 2017cs.CL cs.NEcited by 43

Not on the map. Why?

Abstract (arXiv)

In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer models both outperform the best reported CTC models with a language model, on the popular Hub5'00 benchmark. On our internal diverse dataset, these trends continue - RNNTransducer models rescored with a language model after beam search outperform our best CTC models. These results simplify the speech recognition pipeline so that decoding can now be expressed purely as neural network operations. We also study how the choice of encoder architecture affects the performance of the three models - when all encoder layers are forward only, and when encoders downsample the input representation aggressively.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 17; 2023: 9; 2024: 1; 2025: 1.

43 papers.

Sort:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  2. 2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
  3. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  4. 2021Factorized Neural Transducer for Efficient Language Model Adaptationcited by 31
  5. 2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
  6. 2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 27
  7. 2021On Addressing Practical Challenges for RNN-Transducercited by 19
  8. 2021Pushing the Limits of Non-Autoregressive Speech Recognitioncited by 18
  9. 2021Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognitioncited by 11
  10. 2021Streaming End-to-End ASR based on Blockwise Non-Autoregressive Modelscited by 11
  11. 2022Improving the fusion of acoustic and text representations in RNN-Tcited by 11
  12. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
31 more
  1. 2022Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition modelscited by 11
  2. 2022A Language Agnostic Multilingual Streaming On-Device ASR Systemcited by 9
  3. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  4. 2021A study of latent monotonic attention variantscited by 5
  5. 2022A Likelihood Ratio based Domain Adaptation Method for E2E Modelscited by 5
  6. 2022Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognitioncited by 5
  7. 2023Semi-Autoregressive Streaming ASR With Label Contextcited by 5
  8. 2022Improving CTC-based ASR Models with Gated Interlayer Collaborationcited by 4
  9. 2023On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognitioncited by 4
  10. 2023Seq2seq for Automatic Paraphasia Detection in Aphasic Speechcited by 4
  11. 2021Do End-to-End Speech Recognition Models Care About Context?cited by 3
  12. 2022Memory-Efficient Training of RNN-Transducer with Sampled Softmaxcited by 3
  13. 2022Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognitioncited by 3
  14. 2022Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASRcited by 2
  15. 2022Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR Systemscited by 2
  16. 2023Modality Confidence Aware Training for Robust End-to-End Spoken Language Understandingcited by 2
  17. 2023Key Frame Mechanism For Efficient Conformer Based End-to-end Speech Recognitioncited by 2
  18. 2025Automatic Speech Recognition in the Modern Era: Architectures, Training, and Evaluationcited by 2
  19. 2021HMM-Free Encoder Pre-Training for Streaming RNN Transducercited by 1
  20. 2021VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recordingcited by 1
  21. 2022Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducercited by 1
  22. 2022Leveraging Domain Features for Detecting Adversarial Attacks Against Deep Speech Recognition in Noisecited by 1
  23. 2022SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolutioncited by 1
  24. 2022Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computationcited by 1
  25. 2023Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognitioncited by 1
  26. 2024Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whispercited by 1
  27. 2021Sequence-level self-learning with multiple hypothesescited by 0
  28. 2022BERT-LID: Leveraging BERT to Improve Spoken Language Identificationcited by 0
  29. 2022A Survey of Deep Fake Detection for Trial Courtscited by 0
  30. 2023Enhancing the Unified Streaming and Non-streaming Model with Contrastive Learningcited by 0
  31. 2023Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducercited by 0