论文标题
Genea Challenge 2022的重新入口
The ReprGesture entry to the GENEA Challenge 2022
论文作者
论文摘要
本文介绍了体现药物（Genea）挑战2022年非语言行为的生成和评估的重新入口。基因挑战提供了处理后的数据集并进行了众包评估，以比较不同手势生成系统的性能。在本文中，我们探讨了基于多模式表示学习的自动手势生成系统。我们将WAVLM功能用于音频，FastText功能，用于文本，位置和旋转矩阵功能用于手势。每种模态都投影到两个不同的子空间：模态不变和特定于模态。为了学习模式间不变的共同点并捕获特定于模态表示的字符，在训练过程中使用了基于梯度反向层的对抗分类器和模态重建解码器。手势解码器使用与音频中的节奏相关的所有表示和功能生成适当的手势。我们的代码，预培训的模型和演示可在https://github.com/youngseng/represture上找到。
This paper describes the ReprGesture entry to the Generation and Evaluation of Non-verbal Behaviour for Embodied Agents (GENEA) challenge 2022. The GENEA challenge provides the processed datasets and performs crowdsourced evaluations to compare the performance of different gesture generation systems. In this paper, we explore an automatic gesture generation system based on multimodal representation learning. We use WavLM features for audio, FastText features for text and position and rotation matrix features for gesture. Each modality is projected to two distinct subspaces: modality-invariant and modality-specific. To learn inter-modality-invariant commonalities and capture the characters of modality-specific representations, gradient reversal layer based adversarial classifier and modality reconstruction decoders are used during training. The gesture decoder generates proper gestures using all representations and features related to the rhythm in the audio. Our code, pre-trained models and demo are available at https://github.com/YoungSeng/ReprGesture.
