Comparison of adaptation algorithms for speaker-adaptive HMM-based speech synthesis


Adaptation algorithms
MLLR
CMLLR
SMAPLR
CSMAPLR
SMAPLR+MAP
CSMAPLR+MAP
4oa
4oi


System configuration
Training data for average voice model:SI-84 set of WSJ corpora
Adaptation data: 40 'block adaptation' sentences included in November 1993 CSR H2 task
Model: state-tied context-dependent MSD-HSMMs
Adaptation: algorithms above
Acoustic features: STRAIGHT mel-cepstrum (40-dim), logF0 and aperiodicity + their delta and delta-delta