基于AI的语音播报系统设计及在电台中的应用

Design of AI-based Voice Broadcasting System and Its Application in Radio Station

本文以苏州台AI语音播报系统为对象,介绍了基于语音合成技术和FFmpeg(Fast Forward Mpeg)音频处理技术开发的一套集制作、审核、播出的新闻生产播出系统。该系统采用标签化干预和批量化、模板化、多场景化的制作方式,以及使用FFmpeg音频处理能力对合成语音和垫乐进行动态处理加入淡入淡出效果的合成方式,同时兼顾了本地应急方案的设计,使得该系统更能满足安全播出的需求。

This paper takes AI voice broadcasting system of Suzhou station as the object,and introduces a set of news production and broadcasting system based on speech synthesis technology and FFmpeg audio processing technology that integrates production,review,and broadcasting.The system uses labeling intervention and batch,template,and multi-scene production methods,and uses ffmpeg audio processing ability to dynamically process synthesized speech and pad music,adding a synthesis method of fade-in and fade-out effects.At the same time,it takes into account the design of local emergency scheme,so that the system can better meet the needs of safe broadcasting.