@inproceedings{walsh2023large-scale,
author = {Walsh, Brendan and Hamilton, Mark and Newby, Greg and Wang, Xi and Ruan, Serena and Zhao, Sheng and He, Lei and Zhang, Shaofei and Dettinger, Eric and Freeman, William T. and Weimer, Markus},
title = {Large-Scale Automatic Audiobook Creation},
booktitle = {Interspeech Show and Tell},
year = {2023},
month = {September},
abstract = {An audiobook can dramatically improve a work of literature's accessibility and improve reader engagement. However, audiobooks can take hundreds of hours of human effort to create, edit, and publish. In this work, we present a system that can automatically generate high-quality audiobooks from online e-books. In particular, we leverage recent advances in neural text-to-speech to create and release thousands of human-quality, open-license audiobooks from the Project Gutenberg e-book collection. Our method can identify the proper subset of e-book content to read for a wide collection of diversely structured books and can operate on hundreds of books in parallel. Our system allows users to customize an audiobook's speaking speed and style, emotional intonation, and can even match a desired voice using a small amount of sample audio. This work contributed over five thousand open-license audiobooks and an interactive demo that allows users to quickly create their own customized audiobooks.

Listen to the audiobook collection},
url = {http://approjects.co.za/?big=en-us/research/publication/large-scale-automatic-audiobook-creation/},
}