Man-Machine Speech Communication: 17th National Conference, NCMMSC 2022, Hefei, China, December 15–18, 2022, Proceedings by Ling Zhenhua & Gao Jianqing & Yu Kai & Jia Jia

Author:Ling Zhenhua & Gao Jianqing & Yu Kai & Jia Jia
Language: eng
Format: epub
ISBN: 9789819924011
Publisher: Springer Nature Singapore

2 TTS Model

As the development of deep learning, NN based TTS that adopts deep neural networks as the model backbone for speech synthesis, has now become the mainstream technology for TTS. Compared to the previous TTS systems based on concatenative synthesis and statistical parametric synthesis, the NN based speech synthesis shows conspicuous advantages. It needs less requirement on human pre-processing and feature development, and brings high-quality voice in terms of both intelligibility and naturalness. A NN based TTS system often consists of three basic components: a text analysis module, an acoustic model (abbr. TTS-AM), and a vocoder. The text analysis module converts a text sequence into the linguistic features, and then TTS-AM transforms linguistic features to the acoustic features, finally the vocoder synthesizes the waveform based on the acoustic features.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.