we randomly choose two source speeches from four speakers(SF1, SF3, TM1, TM3) for conversion.

Four Speaker

• SF1 : source female 1
• SF3 : source female 3
• TM1: target male 1
• TM3: target male 3

Conversion results:

• SF1-SF3+200020.wav : source female1’s speech convert to source female2’s speech.
• SF1-TM3+200025.wav : source female1’s speech convert to target male2’s speech.