Generation of Telugu Emotional Speech from Neutral Speech by using Voice Morphing Algorithm
D.Nagaraju1, RJ Ramasree2, N Hari3, V. Pavan Kalyan4, Sk. Shameer5
1D.Nagaraju*, Associate professor in Audisankara College of Engineering and Technology, Gudur, Nellore, (Andhra Pradesh), India.
2Dr. RJ Ramasree, Professor, Dept of Computer Science, Rashtriya Sanskrit Vidyapeetha, Tirupati, Andhra Pradesh, India
3N.Hari, Students in Audisankara College of Engineering and Technology, Gudur, Nellore, (Andhra Pradesh), India.
4V Pavan Kalyan, Students in Audisankara College of Engineering and Technology, Gudur, Nellore, (Andhra Pradesh), India.
5Sk Shameer, Students in Audisankara College of Engineering and Technology, Gudur, Nellore, (Andhra Pradesh), India.
Manuscript received on September 13, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 6001-6004 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1800109119/2019©BEIESP | DOI: 10.35940/ijeat.A1800.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Voice morphing is the conversion of one voice signal into another voice signal i.e. source voice signal into target voice signal. Like image morphing, the aim of speech morphing is to preserve the pooled properties of the source signal and target signal during the generation of a smooth conversion between them. The major properties of speech signal are its pitch and envelope information. Pitch, duration and intensity of speech signal parameters are considered to get emotional voice from neutral or emotion. We are using TD-PSOLA technique to extract the prosodic parameters and during the training phase.
Keywords: Voice morphing Image morphing-emotional voice TD-PSOLA.