Title :
STRAIGHT-TEMPO: a universal tool to manipulate linguistic and para-linguistic speech information
Author :
Kawahara, Hideki
Author_Institution :
Dept. of Design Inf. Sci., Wakayama Univ., Japan
Abstract :
An extremely high-quality speech manipulation method based on the concept of the classic channel vocoder proposed in 1939 is introduced. The proposed method is based on a new view on the role of signal periodicity. The method independently allows for over 600% manipulation of such speech parameters as pitch, vocal tract length, and speaking rate, without introducing further degradation due to parameter manipulation. This enormous flexibility enables controls of linguistic as well as para-linguistic speech information, adding plausible naturalness to simulated artificial speakers, and it also enables natural auditory morphing. These make the proposed method a universal tool for manipulating audio information in multimedia
Keywords :
feature extraction; interpolation; mathematical morphology; smoothing methods; spectral analysis; speech processing; speech synthesis; time-frequency analysis; vocoders; STRAIGHT; adaptive interpolation; auditory morphing; linguistic speech; pitch; signal periodicity; speaking rate; spectrogram; speech information; speech manipulation; speech representation; speech transformation; time frequency analysis; vocal tract length; vocoder; Amplitude modulation; Degradation; Design engineering; Humans; Speech processing; Surface reconstruction; Systems engineering and theory; Time frequency analysis; Vocoders; Wavelet analysis;
Conference_Titel :
Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-4053-1
DOI :
10.1109/ICSMC.1997.638234
