位置：成果数据库 > 期刊 > 期刊详情页
语法信息与韵律结构的分析与预测
  • 期刊名称：中文信息学报
  • 时间：0
  • 页码：65-70
  • 语言：中文
  • 分类：TP391[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
  • 作者机构：[1]清华大学计算机科学与技术系,北京100084
  • 相关基金：基金项目：国家高技术研究发展计划资助项目（2007AA012198）;国家自然科学基金资助项目（60805008,90820304）
  • 相关项目：音视融合的韵律模式的个性化研究
作者： 蔡莲红|王永鑫|
关键词： 计算机应用, 中文信息处理, TTS, 韵律结构, 语法结构, 语义, computer application, Chinese information processing, TTS, prosodic structure, syntactic structure, semantic information
中文摘要：

韵律结构的自动预测是高自然度文语转换（TTS）系统的关键组成部分，直接影响到合成语音的自然度和袁现力。该文建立了一个同时具有语法信息与韵律结构标注的汉语语料库。在这一语料库的基础上，对汉语的韵律结构组成、韵律结构与语法语义之间的关系进行了分析，并进行了预测试验。研究发现，汉语的韵律结构虽与语法结构不同，但是有着密切的联系，韵律结构可以通过语法结构进行预测。韵律结构除与语法结构有关之外，还要受到语句语义的制约。

英文摘要：

Automatic prosody structure prediction is a very important component in high quality Text-to-Speech sys terns which directly affect the naturalness and expressivity of synthesized speech. A text corpus with both syntactic and prosodic structures annotated is constructed. Based on the corpus, the composition of prosody structure and the relationship between syntactic and prosodic structures are analyzed, and a prediction experiment is carried out. The result shows that, though there are differences between the prosodic structure and the syntactic structure in Chi- nese, they have a close relationship the prosodic structure can be predicted by the syntactic structure. The prosodic structure is also affected by the semantic information of the sentence.

同期刊论文项目
音视融合的韵律模式的个性化研究
期刊论文 9 会议论文 16 获奖 1
基于视听觉感知与认知的脑机交互方法与关键技术研究
期刊论文 68 会议论文 15
同项目期刊论文
汉语普通话与沈阳方言转换的研究
面向情感转换的层次化韵律分析与建模
A Unified Framework for Multilingual Text-to-Speech Synthesis with SSML Specification as Interface
基于MPEG-4的人脸表情图像变形研究
Modeling Pitch Contour of Chinese Mandarin Sentences with the PENTA Model
言语信息处理的进展
稳态视觉诱发电位频率与相位特性的脑电研究
An Auditory Brain-Computer Interface Using Active Mental Response
Chirp-modulated visual evoked potential as a generalization of steady state visual evoked potential
无表观特征小目标检测与跟踪
支持隐式人机交互的分布式视觉系统
基于Kinect系统的场景建模与机器人自主导航
基于耳蜗行波理论的线性调频信号刺激听觉稳态反应研究
基于DSP的主动视觉系统
The influence on cognitive processing from the switches of shooting angles in videos of real-world e
基于脑机接口与双激光雷达的移动车导航系统
一种基于运动想象的脑-机接口时空滤波器迭代算法
An ERP study on whether semantic integration exists in processing ecologically unrelated audio-visua
Functional connectivity analysis of steady-state visual evoked potentials
THE INFLUENCE OF MATCHING DEGREES OF SYNCHRONOUS AUDITORY AND VISUAL INFORMATION IN VIDEOS OF REAL-W
Right-and-left visual field stimulation: A frequency and space mixed coding method for SSVEP based b
Emotional Audio-Visual Speech Synthesis Based on PAD
An online brain–computer interface using non-flashing visual evoked potentials
An independent brain–computer interface using covert non-spatial visual selective attention
Emotional facilitation effect in the picture-word interference task: An ERP study
Chinese function words grammaticalized from content words: Evidence from ERPs
相位集聚指数在脑-机接口特征提取中的应用
The effects of punctuations in Chinese sentence comprehension: An ERP study
The interaction between pictures and words: evidence from positivity offset and negativity bias
Cognitive processing of traffic signs in immersive virtual reality environment: An ERP study
SEMANTIC ASSOCIATION OF ECOLOGICALLY UNRELATED SYNCHRONOUS AUDIO-VISUAL INFORMATION IN COGNITIVE INT
Frequency and Phase Mixed Coding in SSVEP-Based Brain-Computer Interface
COGNITIVE INTEGRATION OF ASYNCHRONOUS NATURAL OR NON-NATURAL AUDITORY AND VISUAL INFORMATION IN VIDE
非结构化道路区域检测的协同学习方法
Exploring steady-state visual evoked potentials as an index for intermodal and crossmodal spatial at
Enhancing the classification accuracy of steady-state visual evoked potential-based brain-computer i
基于语义维度的人脸表情生成
用于眼动检测和脑电采集的数据同步方法
An online multi-channel SSVEP-based brain–computer interface using a canonical correlation ana
The integration processing of the visual and auditory information in videos of real-world events: An
移动机器人的改进无迹粒子滤波蒙特卡罗定位算法
VEP-Based Brain-Computer Interfaces: Time, Frequency, and Code Modulations
Spectra-temporal patterns underlying mental addition: An ERP and ERD/ERS study
A coded VEP method to measure interhemispheric transfer time (IHTT)
The pragmatic meanings conveyed by function words in Chinese sentences: An ERP study
Semantic integration of differently asynchronous audio-visual information in videos of real-world ev
一种基于两种不同范式的混合型脑-机接口系统
Identifying major depression using whole-brain functional connectivity: a multivariate pattern analy
基于眼电和稳态视觉诱发电位分析的目光跟踪方法
基于事件相关电位P1的人脸视觉信息早期加工研究
Path Planning Approach Based on Dual Laser Radar Fusion
40 Hz Auditory Steady State Response to Linguistic Features of Stimuli during Auditory Hallucinations
视觉信息处理中的马尔可夫随机场
摄像机几何约束及人体定位