음질 및 속도 향상을 위한 선형 스펙트로그램 활용 Text-to-speechText-to-speech with linear spectrogram prediction for quality and speed improvement
- Other Titles
- Text-to-speech with linear spectrogram prediction for quality and speed improvement
- Authors
- 윤혜빈; 남호성
- Issue Date
- 2021
- Publisher
- 한국음성학회
- Keywords
- speech synthesis; machine learning; artificial intelligence; text-to-speech (TTS)
- Citation
- 말소리와 음성과학, v.13, no.3, pp 71 - 78
- Pages
- 8
- Indexed
- KCI
- Journal Title
- 말소리와 음성과학
- Volume
- 13
- Number
- 3
- Start Page
- 71
- End Page
- 78
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/138207
- DOI
- 10.13064/KSSS.2021.13.3.071
- ISSN
- 2005-8063
- Abstract
- Most neural-network-based speech synthesis models utilize neural vocoders to convert mel-scaled spectrograms into high-quality, human-like voices. However, neural vocoders combined with mel-scaled spectrogram prediction models demand considerable computer memory and time during the training phase and are subject to slow inference speeds in an environment where GPU is not used. This problem does not arise in linear spectrogram prediction models, as they do not use neural vocoders, but these models suffer from low voice quality. As a solution, this paper proposes a Tacotron 2 and Transformer-based linear spectrogram prediction model that produces high-quality speech and does not use neural vocoders. Experiments suggest that this model can serve as the foundation of a high-quality text-to-speech model with fast inference speed.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Liberal Arts > Department of English Language and Literature > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.