当前位置:
X-MOL 学术
›
arXiv.cs.SD
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Excitation-based Voice Quality Analysis and Modification
arXiv - CS - Sound Pub Date : 2020-01-02 , DOI: arxiv-2001.00582 Thomas Drugman, Thierry Dutoit, Baris Bozkurt
arXiv - CS - Sound Pub Date : 2020-01-02 , DOI: arxiv-2001.00582 Thomas Drugman, Thierry Dutoit, Baris Bozkurt
This paper investigates the differences occuring in the excitation for
different voice qualities. Its goal is two-fold. First a large corpus
containing three voice qualities (modal, soft and loud) uttered by the same
speaker is analyzed and significant differences in characteristics extracted
from the excitation are observed. Secondly rules of modification derived from
the analysis are used to build a voice quality transformation system applied as
a post-process to HMM-based speech synthesis. The system is shown to
effectively achieve the transformations while maintaining the delivered
quality.
中文翻译:
基于激励的语音质量分析与修正
本文研究了不同音质在激励中出现的差异。它的目标是双重的。首先分析包含由同一说话者发出的三种语音质量(模态、柔和和响亮)的大型语料库,并观察到从激励中提取的特征的显着差异。其次,来自分析的修改规则用于构建语音质量转换系统,作为基于 HMM 的语音合成的后处理。该系统被证明可以有效地实现转换,同时保持交付的质量。
更新日期:2020-01-06
中文翻译:
基于激励的语音质量分析与修正
本文研究了不同音质在激励中出现的差异。它的目标是双重的。首先分析包含由同一说话者发出的三种语音质量(模态、柔和和响亮)的大型语料库,并观察到从激励中提取的特征的显着差异。其次,来自分析的修改规则用于构建语音质量转换系统,作为基于 HMM 的语音合成的后处理。该系统被证明可以有效地实现转换,同时保持交付的质量。