Skip to main content

Advertisement

Table 2 Average tonal syllable recognition rate (%) after eigenphone-based speaker adaptation using lasso

From: Speaker adaptation based on regularized speaker-dependent eigenphone matrix estimation

λ 1 Number of adaptation sentences
  1 2 4 6 8 10
10 52.25 56.04 58.06 59.06 60.24 61.27
  (0.61) (0.43) (0.23) (0.16) (0.12) (0.04)
20 53.88 56.55 58.54 59.36 60.24 60.83
  (0.83) (0.63) (0.42) (0.33) (0.26) (0.23)
30 53.63 55.96 57.70 59.19 60.05 60.81
  (0.91) (0.74) (0.54) (0.44) (0.37) (0.34)
40 53.82 55.18 57.30 58.90 59.75 60.49
  (0.95) (0.820) (0.65) (0.61) (0.49) (0.42)
  1. The number of eigenphones (N) was fixed to 100. λ2=λ3=0, and λ1 was varied between 10 and 40. The average overall sparsity is shown in parentheses.