Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Sound

• URL: http://arxiv.org/abs/2511.12077v1
• Date: Sat, 15 Nov 2025 07:42:02 GMT
• Title: Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Sound
• Authors: Dengming Zhang, Weitao You, Jingxiong Li, Weishen Lin, Wenda Shi, Xue Zhao, Heda Zuo, Junxian Wu, Lingyun Sun,
• Abstract summary: Art conveys emotion through the joint design of visual and auditory elements, yet most prior work is human-centered or single-modality.<n>We present Vision Anchored Audio-Visual Emotion LLM (VAEmotionLLM), a two-stage framework that teaches a VLM to hear by seeing with limited audio pretraining.<n>VAEmotionLLM achieves state-of-the-art results on ArtEmoBenchmark, outperforming audio-only, visual-only, and audio-visual baselines.
• Score: 21.4061944104446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emotion understanding is critical for making Large Language Models (LLMs) more general, reliable, and aligned with humans. Art conveys emotion through the joint design of visual and auditory elements, yet most prior work is human-centered or single-modality, overlooking the emotion intentionally expressed by the artwork. Meanwhile, current Audio-Visual Language Models (AVLMs) typically require large-scale audio pretraining to endow Visual Language Models (VLMs) with hearing, which limits scalability. We present Vision Anchored Audio-Visual Emotion LLM (VAEmotionLLM), a two-stage framework that teaches a VLM to hear by seeing with limited audio pretraining and to understand emotion across modalities. In Stage 1, Vision-Guided Audio Alignment (VG-Align) distills the frozen visual pathway into a new audio pathway by aligning next-token distributions of the shared LLM on synchronized audio-video clips, enabling hearing without a large audio dataset. In Stage 2, a lightweight Cross-Modal Emotion Adapter (EmoAdapter), composed of the Emotion Enhancer and the Emotion Supervisor, injects emotion-sensitive residuals and applies emotion supervision to enhance cross-modal emotion understanding. We also construct ArtEmoBenchmark, an art-centric emotion benchmark that evaluates content and emotion understanding under audio-only, visual-only, and audio-visual inputs. VAEmotionLLM achieves state-of-the-art results on ArtEmoBenchmark, outperforming audio-only, visual-only, and audio-visual baselines. Ablations show that the proposed components are complementary.

Related papers

• EmoCAST: Emotional Talking Portrait via Emotive Text Description [56.42674612728354]
  EmoCAST is a diffusion-based framework for precise text-driven emotional synthesis.<n>In appearance modeling, emotional prompts are integrated through a text-guided decoupled emotive module.<n>EmoCAST achieves state-of-the-art performance in generating realistic, emotionally expressive, and audio-synchronized talking-head videos.
  arXiv  Detail & Related papers  (2025-08-28T10:02:06Z)
• Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation [26.389793087374432]
  We present an Audio-Visual Language Model (AVLM) for expressive speech generation.<n>We explore multiple visual encoders and multimodal fusion strategies during pre-training to identify the most effective integration approach.
  arXiv  Detail & Related papers  (2025-08-22T08:08:45Z)
• VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection [50.57849622045192]
  We propose VAEmo, an efficient framework for emotion-centric joint VA representation learning with external knowledge injection.<n>VAEmo achieves state-of-the-art performance with a compact design, highlighting the benefit of unified cross-modal encoding and emotion-aware semantic guidance.
  arXiv  Detail & Related papers  (2025-05-05T03:00:51Z)
• Enriching Multimodal Sentiment Analysis through Textual Emotional Descriptions of Visual-Audio Content [56.62027582702816]
  Multimodal Sentiment Analysis seeks to unravel human emotions by amalgamating text, audio, and visual data.<n>Yet, discerning subtle emotional nuances within audio and video expressions poses a formidable challenge.<n>We introduce DEVA, a progressive fusion framework founded on textual sentiment descriptions.
  arXiv  Detail & Related papers  (2024-12-12T11:30:41Z)
• Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion [81.1492897350032]
  Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components. We propose an Attention-based Interactive diseNtangling Network (AINN) that leverages instance-wise emotional knowledge for voice conversion.
  arXiv  Detail & Related papers  (2023-12-29T08:06:45Z)
• Speech Driven Talking Face Generation from a Single Image and an Emotion Condition [28.52180268019401]
  We propose a novel approach to rendering visual emotion expression in speech-driven talking face generation. We design an end-to-end talking face generation system that takes a speech utterance, a single face image, and a categorical emotion label as input. Objective evaluation on image quality, audiovisual synchronization, and visual emotion expression shows that the proposed system outperforms a state-of-the-art baseline system.
  arXiv  Detail & Related papers  (2020-08-08T20:46:31Z)
• Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision [63.564385139097624]
  We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from audio) Our results demonstrate the potential of multimodal self-supervision in audiovisual speech for learning good audio representations.
  arXiv  Detail & Related papers  (2020-07-08T14:07:06Z)
• Visually Guided Self Supervised Learning of Speech Representations [62.23736312957182]
  We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. We achieve state of the art results for emotion recognition and competitive results for speech recognition.
  arXiv  Detail & Related papers  (2020-01-13T14:53:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.