一种数字语音处理研究平台的设计

Design of A Research Platform of Digital Speech Processing

设计了一种支持多视图和多种数据接口的研究平台。该平台采用了模块组合式的体系结构,使得新的语音处理算法能够便捷地加入到平台中。所有模块被分为内部模块和外部模块。内部模块集成语音的数据接口和可视化功能,外部模块则实现语音的分析功能。该平台采用了纵版的显示方式,不同算法得到的结果被垂直排列显示在一个窗口内,有利于对比分析,还内建了支持基于XML的语音标注格式,能够被直接应用到语料库建设和语音分析等领域。

This paper presents a new research platform for visualization of digital speech, which supports multi-view and multi data interface. The modules-combined architecture, employed in the platform, makes new algorithm of speech processing can be quickly embedded. All modules are classified inner modules and extra modules. Data interface and visualization of speech are integrated into inner modules, while analysis procedures are implemented in the extra modules. Vertically arranged in a window, the results of algorithms and procedures can be easily compared and analyzed. ＂lhe presented platform also includes built-in speech XML-based labeling module. Hence, it can be used in the building process of corpus and other fields of speech processing.