Development of Vietnamese speech synthesis system using deep neural networks
Số trang: 15
Loại file: pdf
Dung lượng: 655.01 KB
Lượt xem: 19
Lượt tải: 0
Xem trước 2 trang đầu tiên của tài liệu này:
Thông tin tài liệu:
In this paper, we present our first Vietnamese speech synthesis system based on deep neural networks. To improve the training data collected from the Internet, a cleaning method is proposed. The experimental results indicate that by using deeper architectures we can achieve better performance for the TTS than using shallow architectures such as hidden Markov model.
Nội dung trích xuất từ tài liệu:
Development of Vietnamese speech synthesis system using deep neural networks
Nội dung trích xuất từ tài liệu:
Development of Vietnamese speech synthesis system using deep neural networks
Tìm kiếm theo từ khóa liên quan:
Text-to-speech Speech synthesis Deep neural network Hidden Markov model TTS systemsGợi ý tài liệu liên quan:
-
TTS - VLSP 2021: The NAVI's text-to-speech system for Vietnamese
7 trang 35 0 0 -
XGBoost regression for estimating bearing capacity of concrete piles
9 trang 29 0 0 -
TTS - VLSP 2021: Development of smartcall Vietnamese text-to-speech
7 trang 28 0 0 -
Adapt TTS: High quality zero shot multi-speaker text to speech adaptive based for Vietnamese
15 trang 24 0 0 -
NeuNAC: A novel fragile watermarking algorithm for integrity protection of neural networks
14 trang 22 0 0 -
MLFNN algorithm for speech classification using MMFC feature extraction in a smart wheelchair
7 trang 19 0 0 -
VLSP 2021 - TTS challenge: Vietnamese spontaneous speech synthesis
10 trang 19 0 0 -
TTS - VLSP 2021: The thunder text-to-speech system
7 trang 15 0 0 -
HistoneHMM: Differential analysis of histone modifications with broad genomic footprints
15 trang 10 0 0 -
5 trang 10 0 0