mlsanityData to 7 Oct 2026

Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition

arXiv 2107.02268 ↗First posted 5 Jul 2021cs.CL cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary systems. In practice, however, they often fail to recognize words not seen during training, e.g., named entities, numbers or technical terms. To alleviate this problem we supplement an end-to-end ASR system with a word/phrase memory and a mechanism to access this memory to recognize the words and phrases correctly. After the training of the ASR system, and when it has already been deployed, a relevant word can be added or subtracted instantly without the need for further training. In this paper we demonstrate that through this mechanism our system is able to recognize more than 85% of newly added words that it previously failed to recognize compared to a strong baseline.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

19 of 27 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  3. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  4. 2015Pointer Networkscited by 882
  5. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 632
  6. 2014Neural Turing Machinescited by 630
  7. 2015Listen, Attend and Spellcited by 542
  8. 2014Memory Networkscited by 354
  9. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
  10. 2018How2: A Large-scale Dataset for Multimodal Language Understandingcited by 137
  11. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  12. 2019Two-Pass End-to-End Speech Recognitioncited by 62
7 more
  1. 2016One-shot Learning with Memory-Augmented Neural Networkscited by 60
  2. 2020Deliberation Model Based Two-Pass End-to-End Speech Recognitioncited by 57
  3. 2019Very Deep Self-Attention Networks for End-to-End Speech Recognitioncited by 46
  4. 2019Improving sequence-to-sequence speech recognition training with on-the-fly data augmentationcited by 29
  5. 2019Audio-attention discriminative language model for ASR rescoringcited by 13
  6. 2017Memory-augmented Neural Machine Translationcited by 12
  7. 2019Scalable Multi Corpora Neural Language Models for ASRcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 7; 2024: 6; 2025: 8; 2026: 3.

30 papers.

Sort:

By area:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  2. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  3. 2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
  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. 2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 13
  7. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  8. 2024Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbationcited by 11
  9. 2023Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentationcited by 9
  10. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  11. 2023ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correctioncited by 7
  12. 2022End-to-end Spoken Language Understanding with Tree-constrained Pointer Generatorcited by 6
18 more
  1. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  2. 2025OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabularycited by 4
  3. 2023Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Datacited by 3
  4. 2024Continuously Learning New Words in Automatic Speech Recognitioncited by 3
  5. 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approachcited by 3
  6. 2023DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generationcited by 2
  7. 2025AdaCS: Adaptive Normalization for Enhanced Code-Switching ASRcited by 2
  8. 2024Titanic Calling: Low Bandwidth Video Conference from the Titanic Wreckcited by 1
  9. 2025DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognitioncited by 1
  10. 2025PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decodingcited by 1
  11. 2026When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASRcited by 1
  12. 2026How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMscited by 1
  13. 2022Short-Term Word-Learning in a Dynamically Changing Environmentcited by 0
  14. 2025Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognitioncited by 0
  15. 2025Generative Annotation for ASR Named Entity Correctioncited by 0
  16. 2025PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguationcited by 0
  17. 2025Peeking Into The Future For Contextual Biasingcited by 0
  18. 2026RASST: Retrieval-Augmented Simultaneous Speech Translationcited by 0