Table 2 Average preference for pairwise comparison
From: Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion
Pairs: v1 and v2 | v1% | v2% |
|---|---|---|
1. HMMSS and HMMSS + GV | 36.67 | 63.33 |
2. HMMSS and HMMSS + VC | 31.33 | 68.67 |
3. HMMSS + GV and HMMSS + GV + VC | 50.67 | 49.33 |
4. HMMSS + VC and HMMSS + GV + VC | 51.33 | 48.67 |
5 HMMSS + GV and HMMSS + VC | 46.67 | 53.33 |