# Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization

arXiv: https://arxiv.org/abs/2412.19005 · HTML: https://mlsanity.com/paper/2412.19005/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 26 Dec 2024.

## Builds on (most cited first, 9 of 9)

- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward](https://mlsanity.com/paper/2404.01258/) (2024)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [How2: A Large-scale Dataset for Multimodal Language Understanding](https://mlsanity.com/paper/1811.00347/) (2018)
- [mDPO: Conditional Preference Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2406.11839/) (2024)
- [OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer](https://mlsanity.com/paper/2401.16658/) (2024)
- [Self-Supervised Visual Preference Alignment](https://mlsanity.com/paper/2404.10501/) (2024)
- [SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data](https://mlsanity.com/paper/2408.00624/) (2024)

## Built on by (most cited first, 1 of 1)

- [ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning](https://mlsanity.com/paper/2507.07306/) (2025)

## Abstract (arXiv)

Audiovisual Automatic Speech Recognition (AV-ASR) aims to improve speech recognition accuracy by leveraging visual signals. It is particularly challenging in unconstrained real-world scenarios across various domains due to noisy acoustic environments, spontaneous speech, and the uncertain use of visual information. Most previous works fine-tune audio-only ASR models on audiovisual datasets, optimizing them for conventional ASR objectives. However, they often neglect visual features and common errors in unconstrained video scenarios. In this paper, we propose using a preference optimization strategy to improve speech recognition accuracy for real-world videos. First, we create preference data via simulating common errors that occurred in AV-ASR from two focals: manipulating the audio or vision input and rewriting the output transcript. Second, we propose BPO-AVASR, a Bifocal Preference Optimization method to improve AV-ASR models by leveraging both input-side and output-side preference. Extensive experiments demonstrate that our approach significantly improves speech recognition accuracy across various domains, outperforming previous state-of-the-art models on real-world video speech recognition.