Prior-free Guided TTS: An Improved and Efficient Diffusion-based Text-Guided Speech Synthesis
- Authors
- Choi, Won-Gook; Kim, So-Jeong; Kim, TaeHo; Chang, Joon-Hyuk
- Issue Date
- Aug-2023
- Publisher
- International Speech Communication Association
- Keywords
- diffusion model; guided score; text-to-speech
- Citation
- Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v.2023-August, pp.4289 - 4293
- Indexed
- SCOPUS
- Journal Title
- Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
- Volume
- 2023-August
- Start Page
- 4289
- End Page
- 4293
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/191797
- DOI
- 10.21437/Interspeech.2023-506
- ISSN
- 2308-457X
- Abstract
- Recently, diffusion models have exhibited higher sample quality with guidance, such as classifier guidance and classifier-free guidance. However, these guidances have limitations: they require extra classifiers or joint training, and incur additional sampling cost. In this study, we propose prior-free guidance diffusion model and prior-free guided text-to-speech (PfGuided-TTS) that can generate a speech at a quality as high as other guidances without extra training resources and computational cost. PfGuided-TTS can generate higher human perceptual quality speech than the existing autoregressive (AR) and non-AR models, including diffusion-based TTS on LJSpeech. In addition, we provide a schematic describing why and how classifier- and prior-free guided scores produce high-fidelity samples.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.