Wataru Nakata

J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis

2022 · arXiv (Cornell University)

In this paper, we construct a Japanese audiobook speech corpus called "J-MAC" for speech synthesis research. With the success of reading-style speech synthesis, the research target is shifting to tasks that use complicated contexts. Audiobook …

Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control

2023 · arXiv (Cornell University)

In text-to-speech, controlling voice characteristics is important in achieving various-purpose speech synthesis. Considering the success of text-conditioned generation, such as text-to-image, free-form text instruction should be useful for intuitive and complicated control of voice characteristics. …