arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.03369cs.HC
收藏

语音驱动手势生成的输入输出表示分析

Analyzing Input and Output Representations for Speech-Driven Gesture Generation

Taras Kucherenko, Dai Hasegawa, Gustav Eje Henter, Naoshi Kaneko, Hedvig Kjellström

摘要:

本文提出了一种新的框架,自动语音驱动的手势生成,适用于包括虚拟代理和机器人的人机交互。具体来说,我们通过结合表示学习,扩展了最近基于深度学习的数据驱动方法,用于语音驱动的手势生成。我们的模型将语音作为输入,并以3D坐标序列的形式产生手势作为输出。我们的方法包括两个步骤。首先,我们使用去噪自动编码器神经网络学习人体运动的低维表示,该神经网络由运动编码器MotionE和运动解码器MotionD组成。所学习的表示保留了人类姿势变化的最重要方面,同时去除不太相关的变化。其次,我们训练一种新的编码器网络SpeechE,以从语音映射到具有降低的维度的相应运动表示。在测试时,语音编码器和运动解码器网络被组合:SpeechE基于给定的语音信号预测运动表示,MotionD然后解码这些表示以产生运动序列。我们评估不同的表示尺寸,以找到最有效的表示维数。我们还评估了使用不同的语音特征作为模型输入的效果。我们发现,梅尔频率倒谱系数(MFCC),单独或与韵律特征相结合,表现最好。随后的用户研究结果证实了表示学习的好处。

英文摘要:

This paper presents a novel framework for automatic speech-driven gesture generation, applicable to human-agent interaction including both virtual agents and robots. Specifically, we extend recent deep-learning-based, data-driven methods for speech-driven gesture generation by incorporating representation learning. Our model takes speech as input and produces gestures as output, in the form of a sequence of 3D coordinates. Our approach consists of two steps. First, we learn a lower-dimensional representation of human motion using a denoising autoencoder neural network, consisting of a motion encoder MotionE and a motion decoder MotionD. The learned representation preserves the most important aspects of the human pose variation while removing less relevant variation. Second, we train a novel encoder network SpeechE to map from speech to a corresponding motion representation with reduced dimensionality. At test time, the speech encoder and the motion decoder networks are combined: SpeechE predicts motion representations based on a given speech signal and MotionD then decodes these representations to produce motion sequences. We evaluate different representation sizes in order to find the most effective dimensionality for the representation. We also evaluate the effects of using different speech features as input to the model. We find that mel-frequency cepstral coefficients (MFCCs), alone or combined with prosodic features, perform the best. The results of a subsequent user study confirm the benefits of the representation learning.

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。

↑