EURASIP Journal on Audio, Speech, and Music Processing

Table 4 Singing MUSHRA average scores and 95% confidence interval

From: A unit selection text-to-speech-and-singing synthesis framework from neutral speech: proof of concept

	Configuration	T=100 bpm	T=50 bpm
S7	MLC	62 ± 6	61 ± 7
S4	MLC	59 ± 6	60 ± 6
S0	MLC	60 ± 8	58 ± 7

Best values are in italics

Back to article page