mlsanityData to 13 Oct 2026

Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss

arXiv 2406.16120 ↗First posted 23 Jun 2024eess.AS cs.CL cs.SDcited by 9

Not on the map. Why?

Abstract (arXiv)

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the useful contextual knowledge encoded in the intermediate layers. We hypothesize that employing explicit biasing loss as an auxiliary task in the encoder intermediate layers may better align text tokens or audio frames with the desired objectives. Our proposed intermediate biasing loss brings more regularization and contextualization to the network. Our method outperforms a conventional contextual biasing baseline on the LibriSpeech corpus, achieving a relative improvement of 22.5% in biased word error rate (B-WER) and up to 44% compared to the non-contextual baseline with a biasing list size of 100. Moreover, employing RNN-transducer-driven joint decoding further reduces the unbiased word error rate (U-WER), resulting in a more robust network.

Key facts. Cited by 9 papers in the map (data through 13 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 23 Jun 2024.

Builds on

33 of 43 references.

References · 33

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,844
  2. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 667
  3. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 555
  4. 2015Attention-Based Models for Speech Recognitioncited by 400
  5. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  6. 2018Deep context: end-to-end contextual speech recognitioncited by 137
  7. 2023End-to-End Speech Recognition: A Surveycited by 128
  8. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  9. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
  10. 2020Contextual RNN-T For Open Domain ASRcited by 85
  11. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
  12. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
21 more
  1. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  2. 2020Class LM and word mapping for contextual biasing in End-to-End ASRcited by 42
  3. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  4. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  5. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  6. 2020Improving RNN Transducer Based ASR with Auxiliary Taskscited by 27
  7. 2019Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networkscited by 24
  8. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  9. 2018Hierarchical Multi Task Learning With CTCcited by 20
  10. 2020CIF-based Collaborative Decoding for End-to-end Contextual Speech Recognitioncited by 20
  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
  13. 2022Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systemscited by 17
  14. 2024Improving ASR Contextual Biasing with Guided Attentioncited by 17
  15. 2021Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASRcited by 12
  16. 2023Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognitioncited by 12
  17. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  18. 2023PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducerscited by 10
  19. 2023Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentationcited by 9
  20. 20224D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoderscited by 7
  21. 2023Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languagescited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025ContextASR-Bench: A Massive Contextual Speech Recognition Benchmarkcited by 14
  2. 2025OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabularycited by 4
  3. 2025DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognitioncited by 1
  4. 2025Lightweight Prompt Biasing for Contextualized End-to-End ASR Systemscited by 1
  5. 2025A Neural Model for Contextual Biasing Score Learning and Filteringcited by 1
  6. 2025RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognitioncited by 0
  7. 2026CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASRcited by 0
  8. 2026COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimationcited by 0
  9. 2026BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASRcited by 0