Saved in:
Bibliographic Details
Main Authors: Jung, Jee-weon, Zhang, Wangyou, Maiti, Soumi, Wu, Yihan, Wang, Xin, Kim, Ji-Hoon, Matsunaga, Yuta, Um, Seyun, Tian, Jinchuan, Shim, Hye-jin, Evans, Nicholas, Chung, Joon Son, Takamichi, Shinnosuke, Watanabe, Shinji
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.08711
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Traditional Text-to-Speech (TTS) systems rely on studio-quality speech recorded in controlled settings.a Recently, an effort known as noisy-TTS training has emerged, aiming to utilize in-the-wild data. However, the lack of dedicated datasets has been a significant limitation. We introduce the TTS In the Wild (TITW) dataset, which is publicly available, created through a fully automated pipeline applied to the VoxCeleb1 dataset. It comprises two training sets: TITW-Hard, derived from the transcription, segmentation, and selection of raw VoxCeleb1 data, and TITW-Easy, which incorporates additional enhancement and data selection based on DNSMOS. State-of-the-art TTS models achieve over 3.0 UTMOS score with TITW-Easy, while TITW-Hard remains difficult showing UTMOS below 2.8.