首页 | 本学科首页   官方微博 | 高级检索  
     

A text-to-speech system with high intelligibility and naturalness for Chinese
引用本文:CHU Min and LU Shinan(Institute of Acoustics,Academia Sinica,Beijing 100080). A text-to-speech system with high intelligibility and naturalness for Chinese[J]. 声学学报:英文版, 1996, 0(1)
作者姓名:CHU Min and LU Shinan(Institute of Acoustics  Academia Sinica  Beijing 100080)
作者单位:Institute of Acoustics,Academia Sinica,Beijing 100080
摘    要:I.IntroductionResearchesonChinesesynthesisdisclosethatonlywhenboththesegmentalandsupraseg-melltalfeaturesofthesyntheticspeecharesimilartothoseofthellaturalone,thesyntheticspeechwillsoundintelligibleandnatural[1].Amongekistingsynthetictechniques,theapproachbasedonacousticparametersca-nadustboththesegmentalandsuprasegmentalfeaturesofsyntheticunitsfiekiblyandcanbeconsideredasthemostreasonablesynthetictechniqueintheory.However,theparameterbasedsynthesizerisoverAfependentonthedevelopmentsofparamet…


A text-to-speech system with high intelligibility and naturalness for Chinese
CHU Min and LU Shinan. A text-to-speech system with high intelligibility and naturalness for Chinese[J]. Chinese Journal of Acoustics, 1996, 0(1)
Authors:CHU Min and LU Shinan
Abstract:A Chinese text-to-speech system, which is based on the time domain PitchSynchronous-Overlap-Add (PSOLA) method, with a Chinese syllable dictionary and a prosodicrule dictionaIy, can produce very clear and natural Chinese speech. Research work on naturalness of synthetic Chinese show that, when synthesizing Chinese, pitch, energy, syllable duration and coarticulation between syllables are main factors which affect the naturalness. Among them pitch and duration play the most important roles. The time domain PSOLA scheme provides a method to modify the pitch and duration of a speech segment in time domain, and this makes it possible to adjust the prosody of speech in word level and sentence level, when synthesizing Chinese using waveform concatenation technique. Acoustics analysis of news broadcast speech provides theoretical basis for building up prosodic rules in this system. In this paper the flowchart of the new Chinese text-to-speech system, the research result of acoustics analysis of news broadcast speech, prosodic rules of the new system, and the evaluation results of speech quality of the new system are given.
Keywords:Chinese   Synthesize   Prosodic rule   PSOLA
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号