Statistical Parametric Speech Synthesis using Deep Learning Architectures
本文研究了使用深度學習(Deep Learning)技術與模型的統計參數化語音合成(Statistical Parametric Speech Synthesis)框架。當前語音合成面臨的兩個主要的挑戰在於:採用聲學實現表達語音韻律的複雜度;訓練數據的稀疏性。這兩個問題很大地影響了合成語音的自然度。本文嘗試採用深度學習結構的建模能力,提高合成語音的語音自然度。 === 為了更精確地表示韻律上下文,本文定義了層次韻律結構,用以組織音段與超音段特征。本文採用深度學習結構,運用層次化結構的音節級別表示,構建語音合成系統。 === 受深度置信網絡(Deep Belief Network, DBN)在手...
Other Authors: | Kang, Shiyin (author.) |
---|---|
Format: | Others |
Language: | English Chinese |
Published: |
2016
|
Subjects: | |
Online Access: | http://repository.lib.cuhk.edu.hk/en/item/cuhk-1292251 |
Similar Items
-
Discriminative Multi-Stream Postfilters Based on Deep Learning for Enhancing Statistical Parametric Speech Synthesis
by: Marvin Coto-Jiménez
Published: (2021-02-01) -
Visual speech synthesis using dynamic visemes and deep learning architectures
by: Thangthai, Ausdang
Published: (2018) -
Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
by: Lau, Chee Yong
Published: (2015) -
A Review of Serbian Parametric Speech Synthesis Based on Deep Neural Networks
by: T. Delić, et al.
Published: (2017-06-01) -
An Experimental Analysis of Deep Learning Architectures for Supervised Speech Enhancement
by: Soha A. Nossier, et al.
Published: (2021-12-01)