计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (3): 143-145.

• 数据库、信号与信息处理 • 上一篇    下一篇

一种基于小波和快速傅里叶变换的学习型歌唱系统

潘伟洲,单志龙,邱景钦,袁世超,黄煜廉   

  1. 华南师范大学 计算机学院,广州 510631
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2012-01-21 发布日期:2012-01-21

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

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

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