Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning

Table 1

The correlations of subjective and objective amount of speech.

Objective amount	Subjective amount
	pitch	volume	tone	duration
fundamental frequency	+++	+	++	+
amplitude	+	+++	+	+
spectral envelope	++	+	+++	+
time	+	+	+	+++
Relevance is positively related to the number of ‘+’ s