A novel voice conversion approach using admissible wavelet packet decomposition

EURASIP Journal on Audio, Speech, and Music Processing

Table 2 Performance of baseline method for predicting formant frequencies within a specified percentage of deviation

Transformation model	Formant frequencies	% Predicted frame within deviation
		2%	10%	15%	20%	25%	50%	μ _RMSE	γ₍x, y)
M1-F1	f1	56	82	87	88	89	92	4.36	0.74
	f2	40	77	79	83	85	90	3.63	0.78
	f3	22	61	66	70	73	89	3.25	0.71
	f4	7	23	40	52	65	93	3.05	0.67
F2-M2	f1	51	71	77	79	82	91	3.92	0.65
	f2	44	72	77	82	84	92	3.37	0.57
	f3	29	59	65	70	73	88	3.31	022
	f4	6	39	53	63	74	94	2.91	0.26