A Synthetic Voice for an Assistive Conversational Agent: A Survey to Discover Italian Preferences regarding Synthetic Voice’s Gender and Quality Level

Table 1

Attributed age range values (%) of the voices for each age group. Scores varied from 1 to 5 and reflected age ranges (1 = 19–28 years old; 2 = 29–38 years old; 3 = 39–48 years old; 4 = 49–5 8 years; 5 = 59+ years old).

Age attribution (%)	19–28 years	29–38 years	39–48 years	49–58 years	59+ years
Adolescents	14.13%	35.08%	35.08%	13.09%	2.62%
Young adults	11.67%	47.22%	32.78%	7.22%	1.11%
Middle-aged	11.11%	36.11%	32.78%	14.44%	5.56%
Seniors	3.33%	30%	35.56%	25%	6.11%