How (Not) to Add Laughter to Synthetic Speech
How (Not) to Add Laughter to Synthetic Speech
复制标题
如何（不）在合成语音中添加笑声
DOI：
10.1007/978-3-540-24842-2_23
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
M. Schröder
中科院分区：
文献类型：
--
作者：
Jürgen Trouvain;M. Schröder
笑声是一种强有力的情感表达手段，但尚未用于语音合成。当前的论文报道了一项试点研究，其中将不同类型的笑声与对话情境中的合成语音相结合。感知测试评估了对感知社会联系的影响以及笑声的适当性。结果表明，仔细模拟笑声的强度至关重要，而说话者身份和生成方法似乎不太重要。
Laughter is a powerful means of emotion expression which has not yet been used in speech synthesis. The current paper reports on a pilot study in which differently created types of laughter were combined with synthetic speech in a dialogical situation. A perception test assessed the effect on perceived social bonding as well as the appropriateness of the laughter. Results indicate that it is crucial to carefully model the intensity of the laughter, whereas speaker identity and generation method appear less important.