VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915956876378112 |
|---|---|
| author | Hu, Rui Qiu, Delai Wang, Yining Liu, Shengping Sang, Jitao |
| author_facet | Hu, Rui Qiu, Delai Wang, Yining Liu, Shengping Sang, Jitao |
| contents | Omni-modal large language models (OLLMs) offer a promising end-to-end solution for slide-enhanced speech recognition due to their inherent multimodal capabilities. However, we found a fundamental issue faced by OLLMs: \textit{Visual Interference}, where models show a bias towards visible text over auditory signals, causing them to hallucinate slide content that was never spoken. To address this, we propose Visually-Anchored Policy Optimization (VAPO), which aims to reshape models' inference process to follow the human-like ``Look-then-Listen'' inference chain. Specifically, we design a temporally decoupled policy: the model first extracts visual priors in a <think> block to serve as semantic anchors, then generates the transcription in an <answer> block. The policy is optimized via multi-objective reinforcement learning. Furthermore, we introduce SlideASR-Bench, a comprehensive benchmark designed to address the scarcity of entity-rich data, comprising a large-scale synthetic corpus for training and a challenging real-world test set for evaluation. We conduct extensive evaluations demonstrating that VAPO effectively eliminates visual interference and achieves state-of-the-art performance on SlideASR-Bench and public datasets, significantly reducing entity recognition errors in specialized domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08618 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models Hu, Rui Qiu, Delai Wang, Yining Liu, Shengping Sang, Jitao Audio and Speech Processing Computer Vision and Pattern Recognition Sound Omni-modal large language models (OLLMs) offer a promising end-to-end solution for slide-enhanced speech recognition due to their inherent multimodal capabilities. However, we found a fundamental issue faced by OLLMs: \textit{Visual Interference}, where models show a bias towards visible text over auditory signals, causing them to hallucinate slide content that was never spoken. To address this, we propose Visually-Anchored Policy Optimization (VAPO), which aims to reshape models' inference process to follow the human-like ``Look-then-Listen'' inference chain. Specifically, we design a temporally decoupled policy: the model first extracts visual priors in a <think> block to serve as semantic anchors, then generates the transcription in an <answer> block. The policy is optimized via multi-objective reinforcement learning. Furthermore, we introduce SlideASR-Bench, a comprehensive benchmark designed to address the scarcity of entity-rich data, comprising a large-scale synthetic corpus for training and a challenging real-world test set for evaluation. We conduct extensive evaluations demonstrating that VAPO effectively eliminates visual interference and achieves state-of-the-art performance on SlideASR-Bench and public datasets, significantly reducing entity recognition errors in specialized domains. |
| title | VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models |
| topic | Audio and Speech Processing Computer Vision and Pattern Recognition Sound |
| url | https://arxiv.org/abs/2510.08618 |