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。
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.
出处
《计算机工程与应用》
CSCD
2012年第3期143-145,共3页
Computer Engineering and Applications
基金
国家自然科学基金(No.61102065)
国家大学生创新性试验计划项目(No.091057409)
广州市珠江科技新星项目(No.011)