Voice Conversion Using Pitch Shifting Algorithm by Time Stretching with PSOLA and Re-Sampling

Allam's picture
Journal Title, Volume, Page: 
Journal of Electrical Engineering, Vol. 61, NO. 1, 57–61
Year of Publication: 
Allam Mousa
Electrical Engineering Department, An Najah University, PO Box 7, Nablus, Palestinian Authority
Current Affiliation: 
Department Of Electrical Engineering, Faculty Of Engineering, An-Najah National University, Nablus, Palestine
Preferred Abstract (Original): 
Voice changing has many applications in the industry and commercial filed. This paper emphasizes voice conversion using a pitch shifting method which depends on detecting the pitch of the signal (fundamental frequency) using Simplified Inverse Filter Tracking (SIFT) and changing it according to the target pitch period using time stretching with Pitch Synchronous Over Lap Add Algorithm (PSOLA), then resampling the signal in order to have the same play rate. The same study was performed to see the effect of voice conversion when some Arabic speech signal is considered. Treatment of certain Arabic voiced vowels and the conversion between male and female speech has shown some expansion or compression in the resulting speech. Comparison in terms of pitch shifting is presented here. Analysis was performed for a single frame and a full segmentation of speech.
Voice_Conversion_Using_Pitch_Shifting_Algorithm_By_Time_Stretching_With_Psola_And_Re–Sampling.pdf611.43 KB