Skip to main content

Advertisement

Table 1 The number of leaf nodes for each stream in different speech synthesis systems

From: Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis

  Various speech synthesis systems
HSMM-100 HSMM-200 HSMM-400 HSMM-800 HMEM1 HMEM2
Streams of acoustic features bap 239 392 581 958 565 1,130
dur 124 193 319 512 256 512
log F0 590 904 1,425 2,487 565 1,130
mgc 267 416 736 1,279 695 1,390
Total parameters 75,628 118,314 204,683 354,133 188,217 377,834