We present a large-scale in-the-wild Japanese laughter corpus and a laughter synthesis method. Previous work on laughter synthesis lacks not only data but also proper ways to represent laughter. To solve these problems, we first propose an in-the-wild corpus comprising $3.5$ hours of laughter, which is to our best knowledge the largest laughter corpus designed for laughter synthesis. We then propose pseudo phonetic tokens (PPTs) to represent laughter by a sequence of discrete tokens, which are obtained by training a clustering model on features extracted from laughter by a pretrained self-supervised model. Laughter can then be synthesized by feeding PPTs into a text-to-speech system. We further show PPTs can be used to train a language model for unconditional laughter generation. Results of comprehensive subjective and objective evaluations demonstrate that the proposed method significantly outperforms a baseline method, and can generate natural laughter unconditionally.

翻译：我们提出一个大规模野生日语笑声语料库及一种笑声合成方法。此前关于笑声合成的研究不仅缺乏数据支撑，更缺少恰当的表征方式。为解决这些问题，我们首先构建了一个包含3.5小时笑声的野外语料库——据我们所知，这是目前最大规模专为笑声合成设计的语料库。随后提出伪音素token（PPTs），该方法通过将预训练自监督模型提取的笑声特征输入聚类模型训练，将笑声表征为离散token序列。通过将PPTs输入文本-语音合成系统即可实现笑声合成。进一步研究表明，PPTs可训练用于无条件笑声生成的语言模型。综合主观与客观评估结果表明，所提方法显著优于基线方法，并能无条件生成自然的笑声。