基于频谱建模合成技术的自动音调修正系统  

An Automatic Pitch Correction System Based on Spectral Modeling Synthesis Technique

作　　者：杨楠[1] 

机构地区：[1]华中科技大学电子信息与通信学院,武汉430074

出　　处：《计算机与数字工程》2016年第11期2168-2173,共6页Computer & Digital Engineering

基　　金："十二五"科技支撑计划项目(编号:2014BAK15B04)资助

摘　　要：保留音色的音调修正问题一直是困扰音乐类应用发展的技术难题。论文结合自动修音的应用需求,实现了一套基于频谱建模合成(Spectral Modeling Synthesis,SMS)技术的自动音调修正系统。它通过清浊音判决和音调检测来实时提取歌声的音调(音高),并与正确的参考音调(乐谱)进行对比,确定需要修正的跑调部分,最后采用论文提出的一种基于SMS技术的合成方法对歌声进行音调修正,通过保留其原有的频谱包络来确保修正后音色不变。论文对系统的清浊音判决算法和音调检测算法进行了客观评价,对歌声音调修正效果进行了主观听音评价,均达到了良好的效果。Pitch correction with preservation of timbre has been a difficult technical issue that hinders the development of music applications.To address this problem,a spectral modeling synthesis（SMS）based automatic pitch correction system is proposed.It extracts the pitch contour in real time with voiced/unvoiced decision and pitch detection.The extracted pitch contour is then compared with the reference pitches such that the detuned parts can be determined.Finally,the proposed SMS based method is applied to the voice to correct the pitches,preserving the timbre by preserving the spectral envelop.Experimental results suggest that the proposed system can provide good pitch correction effect.

关 键 词：音调修正 频谱建模合成 清浊音判决 音调检测 

分 类 号：TN912.33[电子电信—通信与信息系统]