mlsanityData to 14 Oct 2026

Contextual Speech Recognition with Difficult Negative Training Examples

arXiv 1810.12170 ↗First posted 29 Oct 2018eess.AS cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with difficult negative examples. The main idea is to focus on proper nouns (e.g., unique entities such as names of people and places) in the reference transcript, and use phonetically similar phrases as negative examples, encouraging the neural model to learn more discriminative representations. We apply our approach to an end-to-end contextual ASR model that jointly learns to transcribe and select the correct context items, and show that our proposed method gives up to 53.1% relative improvement in word error rate (WER) across several benchmarks.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 8; 2024: 6; 2025: 2; 2026: 2.

28 papers.

Sort:

By area:

  1. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  2. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  3. 2021Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognitioncited by 25
  4. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  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. 2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 14
  8. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  9. 2024Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbationcited by 11
  10. 2021Spell my name: keyword boosted speech recognitioncited by 10
  11. 2023Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithmcited by 9
  12. 2023Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognitioncited by 8
16 more
  1. 2022End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention systemcited by 7
  2. 2023Retrieve and Copy: Scaling ASR Personalization to Large Catalogscited by 7
  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. 2024Keyword-Guided Adaptation of Automatic Speech Recognitioncited by 5
  6. 2022Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?cited by 3
  7. 2024Locality enhanced dynamic biasing and sampling strategies for contextual ASRcited by 3
  8. 2024Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrievalcited by 3
  9. 2023The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections through Federated Learningcited by 2
  10. 2024Deep CLAS: Deep Contextual Listen, Attend and Spellcited by 2
  11. 2024Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interviewcited by 1
  12. 2025Improving Contextual ASR via Multi-grained Fusion with Large Language Modelscited by 1
  13. 2025Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modelingcited by 1
  14. 2023Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customizationcited by 0
  15. 2026JSPG: Dynamic Dictionary Filtering via Joint Semantic-Pinyin-Glyph Retrieval for Chinese Contextual ASRcited by 0
  16. 2026No Detectable Change in Side-Level WER from Prompt-Level Context: A Preregistered Ablation on a Production Oral-History Corpuscited by 0