mlsanityData to 7 Oct 2026

Deep context: end-to-end contextual speech recognition

arXiv 1808.02480 ↗First posted 7 Aug 2018eess.AS cs.LG cs.SDcited by 136

Not on the map. Why?

Abstract (arXiv)

In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Listen, Attend and Spell (CLAS) jointly- optimizes the ASR components along with embeddings of the context n-grams. During inference, the CLAS system can be presented with context phrases which might contain out-of- vocabulary (OOV) terms not seen during training. We com- pare our proposed system to a more traditional contextualiza- tion approach, which performs shallow-fusion between inde- pendently trained LAS and contextual n-gram models during beam search. Across a number of tasks, we find that the pro- posed CLAS system outperforms the baseline method by as much as 68% relative WER, indicating the advantage of joint optimization over individually trained components. Index Terms: speech recognition, sequence-to-sequence models, listen attend and spell, LAS, attention, embedded speech recognition.

Key facts. Cited by 136 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 15; 2023: 36; 2024: 29; 2025: 26; 2026: 17.

136 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. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 92
  5. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 75
  6. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  7. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  8. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  9. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  10. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  11. 2021Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognitioncited by 30
  12. 2021Personalization Strategies for End-to-End Speech Recognition Systemscited by 26
38 more
  1. 2021Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognitioncited by 25
  2. 2023End-to-End Speech Recognition Contextualization with Large Language Modelscited by 22
  3. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  4. 2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
  5. 2023Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognitioncited by 18
  6. 2024CTC-Assisted LLM-Based Contextual ASRcited by 18
  7. 2022Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systemscited by 17
  8. 2022Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognitioncited by 17
  9. 2022Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Modelcited by 17
  10. 2024Improving ASR Contextual Biasing with Guided Attentioncited by 17
  11. 2022Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languagescited by 16
  12. 2023SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Abilitycited by 16
  13. 2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 13
  14. 2023Phoneme-aware Encoding for Prefix-tree-based Contextual ASRcited by 13
  15. 2023Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducercited by 12
  16. 2023Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognitioncited by 12
  17. 2021A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systemscited by 11
  18. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  19. 2024Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbationcited by 11
  20. 2021Spell my name: keyword boosted speech recognitioncited by 10
  21. 2024Contextualization of ASR with LLM using phonetic retrieval-based augmentationcited by 10
  22. 2023Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentationcited by 9
  23. 2023Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithmcited by 9
  24. 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 9
  25. 2023Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognitioncited by 8
  26. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  27. 2021Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognitioncited by 7
  28. 2022End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention systemcited by 7
  29. 2023Contextual Biasing of Named-Entities with Large Language Modelscited by 7
  30. 2023ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correctioncited by 7
  31. 2023Retrieve and Copy: Scaling ASR Personalization to Large Catalogscited by 7
  32. 2024Representing Online Handwriting for Recognition in Large Vision-Language Modelscited by 7
  33. 2024Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spottercited by 7
  34. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  35. 2025Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuningcited by 7
  36. 2022End-to-end Spoken Language Understanding with Tree-constrained Pointer Generatorcited by 6
  37. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  38. 2023Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenizationcited by 6

50 most cited of 136 All 136 (JSON)