A Novel Digital Signal Processing Software Text-To-Speech

This paper is a novel digital signal processing software of the advanced conversion of text-to-speech synthesis technology, which has been available as a range of hardware products for more than ten years, to software. It was initially created as a replacement for character cell terminals and telephony applications, but it is now also used to give people who are visually impaired access to information. With a digital formant synthesizer used to mimic the human vocal tract, text-to-speech quality is very high in both understandability and naturalness. The computational requirements of this synthesizer put a tremendous amount of strain on a workstation in the days before extremely fast processors. Multiple text streams were simultaneously converted to speech for this study using a Digital Equipment AlphaModel 600 workstation. Modern RISC processor power enables applications to freely output speech. A text-to-speech application programming interface (API) is now necessary as a result of this capability. The TTS software API we created is compatible with a wide range of hardware and operating systems. The architecture of the TTS software is described in this paper. Additionally, the API is mentioned. Finally, we describe our experience porting the TTS code base from the previous hardware platforms.

本文提出一款新型数字信号处理软件，将已有十余年硬件产品线的先进文本转语音（Text-to-Speech, TTS）合成技术从硬件形态移植至软件平台。该技术最初被开发用于替代字符终端与电信应用场景，如今也被用于为视力障碍群体提供信息获取途径。其采用数字共振峰合成器模拟人类声道，因此文本转语音的可懂度与自然度均处于极高水准。在高性能处理器尚未普及的年代，该合成器的计算开销曾给工作站带来极大负载压力。本研究借助数字设备公司（Digital Equipment）AlphaModel 600工作站，实现了多文本流的并行语音转换。如今，精简指令集处理器（Reduced Instruction Set Computing, RISC）的强劲性能已可支撑应用程序流畅输出语音，由此，文本转语音应用程序编程接口（Application Programming Interface, API）的需求应运而生。我们开发的TTS软件API兼容多种硬件与操作系统平台。本文详述了该TTS软件的整体架构，同时对所提API进行了说明。最后，本文分享了将TTS代码库从原有硬件平台完成移植的实践经验。