A Unified Framework for Multilingual Text-to-Speech Synthesis with SSML Specification as Interface

来源 :清华大学学报(英文版) | 被引量 : 0次 | 上传用户:liang6666
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
This paper describes the design of a unified framework for a multilingual text-to-speech (TTS) synthesis engine -Crystal. The unified framework defines the common TTS modules for different languages and/or dialects. The interfaces between consecutive modules conform to the speech synthesis markup lan-guage (SSML) specification for standardization, interoperability, mulUlinguality, and extensibility. Detailed module divisions and implementation technologies for the unified framework are introduced, together with possible extensions for the algorithm research and evaluation of the TTS synthesis. Implementation of a mixed-language TTS system for Chinese Putonghua, Chinese Cantonese, and English demonstrates the feasibility of the proposed unified framework.
其他文献
首先分析历史街区交通发展面临的问题和困境,在明确历史街区交通发展的价值判断的基础上.构建了历史街区交通规划编制框架,包括规划范围和主要规划内容,与控规衔接的控制和引
本文对遗传算法的基本特点、步骤和流程和基于MATLAB的遗传算法优化工具箱进行了介绍,结合多目标函数问题的优化实例,说明了遗传算法是一种具有良好的全局寻优性能的优化方法
In this paper,it investigates the factors affecting successive brand alliance in which two brands from difierent product categories are featured together to int
Both of Typhoon Winnie (971 1) and Matsa (0509) underwent an extratropical transition (ET)process when they moved northward after landfall and affected l.iaodon
当前,测绘高新技术日新月异的迅猛发展,拓展测绘的发展视野。目前已发展扩大到国民经济和国防建设中与空间数据有关的各个领域。测绘正在适应新形势的需要发生着深刻的变化,并以高新技术为支撑和动力成为信息社会发展的保障。
According to historical records, in July of 1590 A. D., a destructive earthquake occurred near people and domestic animals were killed". In the same month, Bing
In this paper,a fast neural network model for the forecasting of effective points by DEA model is proposed,which is based on the SPDS training algorithm.The SPD
This article investigates the performance of hybrid automatic repeat request (HARQ) with code combining over the ideally interleaved Nakagami-m fading channel.
This article investigates resource allocation in multi-hop orthogonal frequency division multiplexing (OFDM) system with amplifying-and-forwarding relaying to m