The design and application of a speech database for Chinese TTS system
نویسندگان
چکیده
The design and application of a speech database for Mandarin TTS system is presented in this paper. To build a scientific, versatile speech database to meet the call for improving the quality of synthesis units and enhancing previous prosodic models, is the main point of the research. The database structure and contents and the methodology for creating similar database are described, and also some statistics and some research based on the database.
منابع مشابه
Prosodic control in Chinese TTS system
In this paper, the prosodic control strategy is discussed under the collectivity of Chinese TTS system design. A four level (syllable, prosodic word, prosodic phrase and sentence) pitch modification and multiplicative duration model are suggested. Although the prototype of models was formed in 1994, the subsequent results of concerned research based on large speech databases are also represente...
متن کاملDesign and Implementation of an Intelligent Part of Speech Generator
The aim of this paper is to report on an attempt to design and implement an intelligent system capable of generating the correct part of speech for a given sentence while the sentence is totally new to the system and not stored in any database available to the system. It follows the same steps a normal individual does to provide the correct parts of speech using a natural language processor. It...
متن کاملطراحی و ارزیابی یک مدل بازسازی گفتار به روش همگذاری واحدهای حساس به بافت نوایی
This paper describes the design and evaluation of prosodically-sensitive concatenative units for a Persian text-to-speech (TTS) synthesis system. Thesyllables used are prosodically conditioned in the sense that a single conventional syllable is stored as different versions taken directly from the different prosodic domains of the prosodically labeled, read sentences. The three levels of the Per...
متن کاملData pruning approach to unit selection for inventory generation of concatenative embeddable Chinese TTS systems
In this paper, a data pruning approach is presented for building acoustic unit inventory for syllable-based concatenative embeddable Chinese TTS system. A 3-portion segmentation of a syllable is proposed based on the nature of voiced/unvoiced structure of Chinese syllable. Individual factorial acoustic measurement of syllable is used to calculate the penalty of perceptual unsatisfactory for con...
متن کاملA Novel Method for Speech Data Mining
Text-to-Speech (TTS) system is one to translate given text to speech which can be used in various applications such as information releasing systems, voice response devices, voice services in E-mail and reading machines for the blind. Great progress has been made in the research on Chinese TTS systems and several Chinese TTS systems have been published. However, because of the complexity of Chi...
متن کامل