Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| 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!
|
| _version_ | 1866916770767437824 |
|---|---|
| author | 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 |
| author_facet | 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 |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08711 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Text-To-Speech Synthesis In The Wild 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 Audio and Speech Processing Artificial Intelligence 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. |
| title | Text-To-Speech Synthesis In The Wild |
| topic | Audio and Speech Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2409.08711 |