EURASIP Journal on Audio, Speech, and Music Processing

Table 3 Time-scale factor (β) percentages obtained with the S4pdLC configuration at 100 bpm and 50 bpm for different note durations (in ms)

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

Note	β			Note	β
dur(ms)	≤ 2.5	(2.5–4]	> 4	dur(ms)	≤ 2.5	(2.5–4]	> 4
600	9.0	23.5	67.5	1200	0.0	0.2	99.8
300	55.1	29.7	15.2	600	3.5	8.4	88.1
150	97.8	1.8	0.3	300	50.1	32.6	17.4

Back to article page