mlsanityData to 7 Oct 2026

Hybrid Autoregressive Transducer (hat)

arXiv 2003.07705 ↗First posted 12 Mar 2020eess.AS cs.CL cs.LGcited by 106

Not on the map. Why?

Abstract (arXiv)

This paper proposes and evaluates the hybrid autoregressive transducer (HAT) model, a time-synchronous encoderdecoder model that preserves the modularity of conventional automatic speech recognition systems. The HAT model provides a way to measure the quality of the internal language model that can be used to decide whether inference with an external language model is beneficial or not. This article also presents a finite context version of the HAT model that addresses the exposure bias problem and significantly simplifies the overall training and inference. We evaluate our proposed model on a large-scale voice search task. Our experiments show significant improvements in WER compared to the state-of-the-art approaches.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 32; 2023: 33; 2024: 8; 2025: 10; 2026: 1.

106 papers.

Sort:

By area:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  2. 2023End-to-End Speech Recognition: A Surveycited by 127
  3. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  4. 2023Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognitioncited by 48
  5. 2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
  6. 2021Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognitioncited by 37
  7. 2021Tied & Reduced RNN-T Decodercited by 35
  8. 2021SynthASR: Unlocking Synthetic Data for Speech Recognitioncited by 34
  9. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  10. 2021Factorized Neural Transducer for Efficient Language Model Adaptationcited by 31
  11. 2021Librispeech Transducer Model with Internal Language Model Prior Correctioncited by 26
  12. 2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
38 more
  1. 2022Pseudo Label Is Better Than Human Labelcited by 25
  2. 2022Scaling Language Model Size in Cross-Device Federated Learningcited by 25
  3. 2021Injecting Text in Self-Supervised Speech Pretrainingcited by 24
  4. 2022JOIST: A Joint Speech and Text Streaming Model For ASRcited by 24
  5. 2021Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognitioncited by 19
  6. 2021Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognitioncited by 17
  7. 2021On Language Model Integration for RNN Transducer based Speech Recognitioncited by 17
  8. 2022E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASRcited by 17
  9. 2022Modular Hybrid Autoregressive Transducercited by 17
  10. 2023Mixture-of-Expert Conformer for Streaming Multilingual ASRcited by 17
  11. 2022Efficient Training of Neural Transducer for Speech Recognitioncited by 14
  12. 2023Large-scale Language Model Rescoring on Long-form Datacited by 14
  13. 2021Streaming Multi-talker Speech Recognition with Joint Speaker Identificationcited by 12
  14. 2022Improving Rare Word Recognition with LM-aware MWER Trainingcited by 12
  15. 2021Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognitioncited by 11
  16. 2022Improving the fusion of acoustic and text representations in RNN-Tcited by 11
  17. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  18. 2022Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition modelscited by 11
  19. 2022Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognitioncited by 10
  20. 2022Global Normalization for Streaming Speech Recognition in a Modular Frameworkcited by 10
  21. 2025Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planningcited by 10
  22. 2021Lookup-Table Recurrent Language Models for Long Tail Speech Recognitioncited by 9
  23. 2022Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASRcited by 9
  24. 2022Detecting Unintended Memorization in Language-Model-Fused ASRcited by 9
  25. 2023JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognitioncited by 9
  26. 2021On Architectures and Training for Raw Waveform Feature Extraction in ASRcited by 8
  27. 2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architecturescited by 8
  28. 2022USTED: Improving ASR with a Unified Speech and Text Encoder-Decodercited by 7
  29. 2023Powerful and Extensible WFST Framework for RNN-Transducer Lossescited by 7
  30. 2023Modular Domain Adaptation for Conformer-Based Streaming ASRcited by 7
  31. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  32. 2022Neural-FST Class Language Model for End-to-End Speech Recognitioncited by 6
  33. 2022UserLibri: A Dataset for ASR Personalization Using Only Textcited by 6
  34. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  35. 2023CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognitioncited by 6
  36. 2021Equivalence of Segmental and Neural Transducer Modeling: A Proof of Conceptcited by 5
  37. 2022Adaptive Discounting of Implicit Language Models in RNN-Transducerscited by 5
  38. 2022Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognitioncited by 5

50 most cited of 106 All 106 (JSON)