Computer Engineering and Applications ›› 2012, Vol. 48 ›› Issue (3): 143-145.

• 数据库、信号与信息处理 • Previous Articles     Next Articles

Intelligent singing system based on wavelets transform and fast Fourier transform

PAN Weizhou, SHAN Zhilong, QIU Jingqin, YUAN Shichao, HUANG Yulian   

  1. School of Computer, South China Normal University, Guangzhou 510631, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2012-01-21 Published:2012-01-21



  1. 华南师范大学 计算机学院,广州 510631

Abstract: Speech recognition and text to speech technologies enable computers to understand human languages and read as a human respectively. In this paper, an intelligent singing system is proposed. The system uses percussion locating method to locate every moment when each word of lyric occurs. Daubechies Wavelets Transform(DWT) and Fast Fourier Transform(FFT) are used to calculate the fundamental frequency. The computer sings the song with text to speech technology.

Key words: Melody Lyric to Song(MLTS), singing, Daubechies Wavelets Transform(DWT), Fast Fourier Transform(FFT), text to speech

摘要: 语音识别和合成技术分别实现了计算机理解人类语言和模仿人类阅读文本的功能,提出了一种实现计算机学习并演唱歌曲的系统。系统运用敲击定位法定位发音时刻,然后利用Daubechies小波变换和快速傅里叶变换计算出对应的基频,采用语音合成技术输出声音。

关键词: MLTS技术, 歌唱, Daubechies小波变换, 快速傅里叶变换, 语音合成