mlsanityData to 7 Oct 2026

Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition

arXiv 2109.00627 ↗First posted 1 Sep 2021cs.CL cs.SDcited by 32

Not on the map. Why?

Abstract (arXiv)

Contextual knowledge is important for real-world automatic speech recognition (ASR) applications. In this paper, a novel tree-constrained pointer generator (TCPGen) component is proposed that incorporates such knowledge as a list of biasing words into both attention-based encoder-decoder and transducer end-to-end ASR models in a neural-symbolic way. TCPGen structures the biasing words into an efficient prefix tree to serve as its symbolic input and creates a neural shortcut between the tree and the final ASR output distribution to facilitate recognising biasing words during decoding. Systems were trained and evaluated on the Librispeech corpus where biasing words were extracted at the scales of an utterance, a chapter, or a book to simulate different application scenarios. Experimental results showed that TCPGen consistently improved word error rates (WERs) compared to the baselines, and in particular, achieved significant WER reductions on the biasing words. TCPGen is highly efficient: it can handle 5,000 biasing words and distractors and only add a small overhead to memory use and computation cost.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 37 of its 52 references that are in the map. First posted on arXiv 1 Sep 2021.

Builds on

37 of 52 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  5. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  6. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  7. 2015Listen, Attend and Spellcited by 542
  8. 2015Attention-Based Models for Speech Recognitioncited by 400
  9. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  10. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
  11. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 148
  12. 2018Deep context: end-to-end contextual speech recognitioncited by 136
25 more
  1. 2017An analysis of incorporating an external language model into a sequence-to-sequence modelcited by 109
  2. 2020Hybrid Autoregressive Transducer (hat)cited by 106
  3. 2016Towards better decoding and language model integration in sequence to sequence modelscited by 100
  4. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  5. 2020Contextual RNN-T For Open Domain ASRcited by 85
  6. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  7. 2019Improving RNN Transducer Modeling for End-to-End Speech Recognitioncited by 68
  8. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
  9. 2017Exploring Neural Transducers for End-to-End Speech Recognitioncited by 43
  10. 2020Class LM and word mapping for contextual biasing in End-to-End ASRcited by 42
  11. 2019Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversationscited by 41
  12. 2021Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognitioncited by 37
  13. 2018Improved training of end-to-end attention models for speech recognitioncited by 35
  14. 2020Joint Contextual Modeling for ASR Correction and Language Understandingcited by 30
  15. 2018Back-Translation-Style Data Augmentation for End-to-End ASRcited by 28
  16. 2018Contextual Speech Recognition with Difficult Negative Training Examplescited by 28
  17. 2018End-to-end contextual speech recognition using class language models and a token passing decodercited by 26
  18. 2017Towards End-to-End Speech Recognition with Deep Convolutional Neural Networkscited by 24
  19. 2018End-to-end Speech Recognition with Word-based RNN Language Modelscited by 23
  20. 2020Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducercited by 22
  21. 2020Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Modelcited by 11
  22. 2018Contextual Language Model Adaptation for Conversational Agentscited by 10
  23. 2019Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognitioncited by 8
  24. 2020Fast and Robust Unsupervised Contextual Biasing for Speech Recognitioncited by 7
  25. 2020Modular End-to-end Automatic Speech Recognition Framework for Acoustic-to-word Modelcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 11; 2024: 6; 2025: 6; 2026: 2.

32 papers.

Sort:

By area:

  1. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  2. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  3. 2023PromptASR for contextualized ASR with controllable stylecited by 18
  4. 2022Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systemscited by 17
  5. 2022Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognitioncited by 17
  6. 2022Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Modelcited by 17
  7. 2023Phoneme-aware Encoding for Prefix-tree-based Contextual ASRcited by 13
  8. 2023Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognitioncited by 12
  9. 2022Improving the fusion of acoustic and text representations in RNN-Tcited by 11
  10. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  11. 2023Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentationcited by 9
  12. 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 9
20 more
  1. 2023Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognitioncited by 8
  2. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  3. 2022End-to-end Spoken Language Understanding with Tree-constrained Pointer Generatorcited by 6
  4. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  5. 2023Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducercited by 6
  6. 2023Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimationcited by 5
  7. 2024Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Modelcited by 5
  8. 2022Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?cited by 3
  9. 2023Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Datacited by 3
  10. 2024Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrievalcited by 3
  11. 2025Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciationcited by 3
  12. 2024Deep CLAS: Deep Contextual Listen, Attend and Spellcited by 2
  13. 2024An Effective Context-Balanced Adaptation Approach for Long-Tailed Speech Recognitioncited by 1
  14. 2025Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activationcited by 1
  15. 2025Lightweight Prompt Biasing for Contextualized End-to-End ASR Systemscited by 1
  16. 2025PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decodingcited by 1
  17. 2025Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modelingcited by 1
  18. 2025A Neural Model for Contextual Biasing Score Learning and Filteringcited by 1
  19. 2026TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognitioncited by 0
  20. 2026No Detectable Change in Side-Level WER from Prompt-Level Context: A Preregistered Ablation on a Production Oral-History Corpuscited by 0