用个人视频生成有情绪的外语提问，提升语言学习沉浸感
Re:Member: Emotional Question Generation from Personal Memories
- 基于用户视频生成带情绪的外语口语问题
- 通过视觉上下文匹配语气，如低语、深夜语调
- 适合关注情感化学习的教育科技研究者
我们提出 Re:Member 系统，探索情绪化、基于个人记忆的交互如何提升第二语言（L2）学习的参与度。该系统利用用户个人视频，生成目标语言中的风格化口语问题，旨在促进情感回忆与对话互动。系统通过表达性语音风格（如低语、深夜语调）与视觉情境对齐，营造特定情绪氛围。采用 WhisperX 进行语音转录对齐，3帧视觉采样提取上下文，结合 Style-BERT-VITS2 实现情感化语音合成，构建模块化生成流程。作为风格化交互探针，Re:Member 强调情感与个人媒体在以学习者为中心的教育技术中的作用。
原文摘要 · Abstract (English)
We present Re:Member, a system that explores how emotionally expressive, memory-grounded interaction can support more engaging second language (L2) learning. By drawing on users' personal videos and generating stylized spoken questions in the target language, Re:Member is designed to encourage affective recall and conversational engagement. The system aligns emotional tone with visual context, using expressive speech styles such as whispers or late-night tones to evoke specific moods. It combines WhisperX-based transcript alignment, 3-frame visual sampling, and Style-BERT-VITS2 for emotional synthesis within a modular generation pipeline. Designed as a stylized interaction probe, Re:Member highlights the role of affect and personal media in learner-centered educational technologies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。