Post by thelastmonolith on Aug 14, 2014 21:26:20 GMT -5
Hi all! I'm taking up my thesis1 as an Electronics Engineering student and I'm deeply interested in DSP(digital signal processing). My time line for this research is about 4 months.
I need suggestions about how to create or mimic one's voice. A voice is sampled and it is then used to modulate any other voice.
There is already an existing technology for Text-to-speech. This technique uses a large database of recordings of one person's voice uttering a long collection of sentences - selected so that the largest number of phoneme combinations are present.
I would like to know if A could copy B's voice through voice conversions.
Thanks for your time mate!
Have any thesis/projects ideas to share related to Electronics? Please I'm open to hear other topics for my thesis.
THANKS again!
I need suggestions about how to create or mimic one's voice. A voice is sampled and it is then used to modulate any other voice.
There is already an existing technology for Text-to-speech. This technique uses a large database of recordings of one person's voice uttering a long collection of sentences - selected so that the largest number of phoneme combinations are present.
I would like to know if A could copy B's voice through voice conversions.
Thanks for your time mate!
Have any thesis/projects ideas to share related to Electronics? Please I'm open to hear other topics for my thesis.
THANKS again!