arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08293eess.AS
收藏

跨模态瓶颈融合用于噪声鲁棒的音频视觉语音识别

Cross-Modal Bottleneck Fusion For Noise Robust Audio-Visual Speech Recognition

Seoul National University(首尔大学)

Seaone Ok, Min Jun Choi, Eungbeom Kim, Seungu Han, Kyogu Lee

AI总结:

CoBRA通过跨模态瓶颈融合机制,在噪声环境下提升音频视觉语音识别的鲁棒性和效率。

摘要:

音频视觉语音识别(AVSR)利用音频和视觉线索来在嘈杂环境下提高语音识别性能。一个核心问题是如何设计一种融合机制,使模型能够在音频信号退化时有效利用视觉信息,同时在干净语音上保持强劲性能。我们提出了CoBRA(跨模态瓶颈用于鲁棒AVSR),一种基于瓶颈的融合框架,引入了一组可学习的令牌来调解跨模态交换。通过调节这些令牌的信息流,即使在恶劣或超出领域噪声下,音频流也能可靠地访问关键的视觉线索。尽管训练数据有限,我们的模型超越了可比的基线,并通过噪声自适应融合与大规模系统保持竞争力,展示了效率和鲁棒性。消融研究显示,融合深度是最重要的因素,突显了其在设计鲁棒AVSR系统中的重要性。

英文摘要:

Audio-Visual Speech Recognition (AVSR) leverages both acoustic and visual cues to improve speech recognition under noisy conditions. A central question is how to design a fusion mechanism that allows the model to effectively exploit visual information when the audio signal is degraded, while maintaining strong performance on clean speech. We propose CoBRA (Cross-modal Bottleneck for Robust AVSR), a bottleneck-based fusion framework that introduces a compact set of learnable tokens to mediate cross-modal exchange. By regulating information flow through these tokens, the audio stream can reliably access essential visual cues even under adverse or out-of-domain noise. Despite limited training data, our model surpasses comparable baselines and remains competitive with large-scale systems through noise-adaptive fusion, demonstrating both efficiency and robustness. Ablation studies highlight that the depth of fusion is the most critical factor, underscoring its importance in designing robust AVSR systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑