# Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus

arXiv: https://arxiv.org/abs/2305.12442 · HTML: https://mlsanity.com/paper/2305.12442/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2023.

## Built on by (most cited first, 5 of 5)

- [Towards human-like spoken dialogue generation between AI agents from written dialogue](https://mlsanity.com/paper/2310.01088/) (2023)
- [Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like](https://mlsanity.com/paper/2402.07383/) (2024)
- [Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model](https://mlsanity.com/paper/2309.11000/) (2023)
- [Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition](https://mlsanity.com/paper/2405.00307/) (2024)
- [MultiLinguahah : A New Unsupervised Multilingual Acoustic Laughter Segmentation Method](https://mlsanity.com/paper/2605.06309/) (2026)

## Abstract (arXiv)

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.