# LCB-net: Long-Context Biasing for Audio-Visual Speech Recognition

arXiv: https://arxiv.org/abs/2401.06390 · HTML: https://mlsanity.com/paper/2401.06390/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2024.

## Built on by (most cited first, 6 of 6)

- [SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing](https://mlsanity.com/paper/2601.09385/) (2026)
- [Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides](https://mlsanity.com/paper/2504.15066/) (2025)
- [PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding](https://mlsanity.com/paper/2506.11064/) (2025)
- [Improving Contextual ASR via Multi-grained Fusion with Large Language Models](https://mlsanity.com/paper/2507.12252/) (2025)
- [How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs](https://mlsanity.com/paper/2608.05759/) (2026)
- [Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognition](https://mlsanity.com/paper/2506.18703/) (2025)

## Abstract (arXiv)

The growing prevalence of online conferences and courses presents a new challenge in improving automatic speech recognition (ASR) with enriched textual information from video slides. In contrast to rare phrase lists, the slides within videos are synchronized in real-time with the speech, enabling the extraction of long contextual bias. Therefore, we propose a novel long-context biasing network (LCB-net) for audio-visual speech recognition (AVSR) to leverage the long-context information available in videos effectively. Specifically, we adopt a bi-encoder architecture to simultaneously model audio and long-context biasing. Besides, we also propose a biasing prediction module that utilizes binary cross entropy (BCE) loss to explicitly determine biased phrases in the long-context biasing. Furthermore, we introduce a dynamic contextual phrases simulation to enhance the generalization and robustness of our LCB-net. Experiments on the SlideSpeech, a large-scale audio-visual corpus enriched with slides, reveal that our proposed LCB-net outperforms general ASR model by 9.4%/9.1%/10.9% relative WER/U-WER/B-WER reduction on test set, which enjoys high unbiased and biased performance. Moreover, we also evaluate our model on LibriSpeech corpus, leading to 23.8%/19.2%/35.4% relative WER/U-WER/B-WER reduction over the ASR model.