mlsanityData to 7 Oct 2026

Improving ASR Contextual Biasing with Guided Attention

arXiv 2401.08835 ↗First posted 16 Jan 2024cs.CL eess.AScited by 17

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the effectiveness and robustness of automatic speech recognition (ASR) contextual biasing without introducing additional parameters. A common challenge in previous literature is that the word error rate (WER) reduction brought by contextual biasing diminishes as the number of bias phrases increases. To address this challenge, we employ a GA loss as an additional training objective besides the Transducer loss. The proposed GA loss aims to teach the cross attention how to align bias phrases with text tokens or audio frames. Compared to studies with similar motivations, the proposed loss operates directly on the cross attention weights and is easier to implement. Through extensive experiments based on Conformer Transducer with Contextual Adapter, we demonstrate that the proposed method not only leads to a lower WER but also retains its effectiveness as the number of bias phrases increases. Specifically, the GA loss decreases the WER of rare vocabularies by up to 19.2% on LibriSpeech compared to the contextual biasing baseline, and up to 49.3% compared to a vanilla Transducer.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 16 Jan 2024.

Builds on

21 of 29 references.

References · 21

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  2. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  3. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  4. 2015Listen, Attend and Spellcited by 542
  5. 2015Attention-Based Models for Speech Recognitioncited by 400
  6. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  7. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  8. 2020Contextual RNN-T For Open Domain ASRcited by 85
  9. 2020CTC-Segmentation of Large Corpora for German End-to-end Speech Recognitioncited by 75
  10. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
  11. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  12. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
9 more
  1. 2020Class LM and word mapping for contextual biasing in End-to-End ASRcited by 42
  2. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  3. 2021Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognitioncited by 25
  4. 2023Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognitioncited by 18
  5. 2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 13
  6. 2023Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducercited by 12
  7. 2023Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognitioncited by 12
  8. 2023Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languagescited by 4
  9. 2022Multi-task RNN-T with Semantic Decoder for Streamable Spoken Language Understandingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 7; 2026: 5.

17 papers.

Sort:

By area:

  1. 2024CTC-Assisted LLM-Based Contextual ASRcited by 18
  2. 2024Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbationcited by 11
  3. 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 9
  4. 2026SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processingcited by 7
  5. 2025Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciationcited by 3
  6. 2026IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languagescited by 3
  7. 2024An Effective Context-Balanced Adaptation Approach for Long-Tailed Speech Recognitioncited by 1
  8. 2025PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decodingcited by 1
  9. 2025Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modelingcited by 1
  10. 2025Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Functioncited by 1
  11. 2025A Neural Model for Contextual Biasing Score Learning and Filteringcited by 1
  12. 2024An Efficient Self-Learning Framework For Interactive Spoken Dialog Systemscited by 0
5 more
  1. 2025PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguationcited by 0
  2. 2025Peeking Into The Future For Contextual Biasingcited by 0
  3. 2026CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASRcited by 0
  4. 2026From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMscited by 0
  5. 2026In-Context Adaptation of Encoder-Decoder Models in Speech Recognitioncited by 0