mlsanityData to 7 Oct 2026

Contextual RNN-T For Open Domain ASR

arXiv 2006.03411 ↗First posted 4 Jun 2020eess.AS cs.CL cs.LGcited by 85

Not on the map. Why?

Abstract (arXiv)

End-to-end (E2E) systems for automatic speech recognition (ASR), such as RNN Transducer (RNN-T) and Listen-Attend-Spell (LAS) blend the individual components of a traditional hybrid ASR system - acoustic model, language model, pronunciation model - into a single neural network. While this has some nice advantages, it limits the system to be trained using only paired audio and text. Because of this, E2E models tend to have difficulties with correctly recognizing rare words that are not frequently seen during training, such as entity names. In this paper, we propose modifications to the RNN-T model that allow the model to utilize additional metadata text with the objective of improving performance on these named entity words. We evaluate our approach on an in-house dataset sampled from de-identified public social media videos, which represent an open domain ASR task. By using an attention model and a biasing model to leverage the contextual metadata that accompanies a video, we observe a relative improvement of about 16% in Word Error Rate on Named Entities (WER-NE) for videos with related metadata.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 23; 2024: 16; 2025: 13; 2026: 9.

85 papers.

Sort:

By area:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  2. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  3. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  4. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  5. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 46
  6. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  7. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  8. 2021Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognitioncited by 25
  9. 2023End-to-End Speech Recognition Contextualization with Large Language Modelscited by 22
  10. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  11. 2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
  12. 2023Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognitioncited by 18
38 more
  1. 2024CTC-Assisted LLM-Based Contextual ASRcited by 18
  2. 2022Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systemscited by 17
  3. 2022Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognitioncited by 17
  4. 2022Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Modelcited by 17
  5. 2024Improving ASR Contextual Biasing with Guided Attentioncited by 17
  6. 2023SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Abilitycited by 16
  7. 2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 13
  8. 2023Phoneme-aware Encoding for Prefix-tree-based Contextual ASRcited by 13
  9. 2023Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducercited by 12
  10. 2021A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systemscited by 11
  11. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  12. 2024Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbationcited by 11
  13. 2021Spell my name: keyword boosted speech recognitioncited by 10
  14. 2023Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentationcited by 9
  15. 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 9
  16. 2023Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognitioncited by 8
  17. 2023Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASRcited by 8
  18. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  19. 2023Contextual Biasing of Named-Entities with Large Language Modelscited by 7
  20. 2024Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spottercited by 7
  21. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  22. 2022End-to-end Spoken Language Understanding with Tree-constrained Pointer Generatorcited by 6
  23. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  24. 2023Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducercited by 6
  25. 2022CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signalscited by 5
  26. 2023Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimationcited by 5
  27. 2021Attention-based Contextual Language Model Adaptation for Speech Recognitioncited by 4
  28. 2023On-the-fly Text Retrieval for End-to-End ASR Adaptationcited by 4
  29. 2023Dialog act guided contextual adapter for personalized speech recognitioncited by 4
  30. 2023SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappingscited by 4
  31. 2024DANCER: Entity Description Augmented Named Entity Corrector for Automatic Speech Recognitioncited by 4
  32. 2025OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabularycited by 4
  33. 2025TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Treecited by 4
  34. 2022Unified Modeling of Multi-Domain Multi-Device ASR Systemscited by 3
  35. 2023A Token-Wise Beam Search Algorithm for RNN-Tcited by 3
  36. 2024Promptformer: Prompted Conformer Transducer for ASRcited by 3
  37. 2024Locality enhanced dynamic biasing and sampling strategies for contextual ASRcited by 3
  38. 2024Text Injection for Neural Contextual Biasingcited by 3

50 most cited of 85 All 85 (JSON)