利用 WaveNet 从语音进行动态倾听头部建模
Leveraging WaveNet for Dynamic Listening Head Modeling from Speech
AI总结:
本文提出结合 WaveNet 与 LSTM 的序列到序列模型,由单人语音生成真实可信的倾听者头部反应视频,并在 ViCo benchmark Dataset 上超过基线模型。
摘要:
倾听者面部反应的生成旨在模拟面对面交谈中倾听者的互动交流反馈。我们的目标是通过一种结合 WaveNet 与长短期记忆网络的序列到序列模型,生成可信的倾听者头部视频,使其对单个说话者作出真实反应。我们的方法侧重于捕捉倾听者反馈的细微差别,在表达恰当态度和观点的同时,确保保留个体倾听者的身份。实验结果表明,我们的方法在 ViCo benchmark Dataset 上优于基线模型。
英文摘要:
The creation of listener facial responses aims to simulate interactive communication feedback from a listener during a face-to-face conversation. Our goal is to generate believable videos of listeners' heads that respond authentically to a single speaker by a sequence-to-sequence model with an combination of WaveNet and Long short-term memory network. Our approach focuses on capturing the subtle nuances of listener feedback, ensuring the preservation of individual listener identity while expressing appropriate attitudes and viewpoints. Experiment results show that our method surpasses the baseline models on ViCo benchmark Dataset.
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。