Diverse speakers' HTS voices trained on non-speech synthesis corpora:
Audio Examples

Finnish Speecon database

Robust speaker-adaptive speech synthesis system 'HTS-2007'

Speaker's ID Number of adaptation sentences Utterance 1 Utterance 2 Utterance 3
001 29 sentences wav wav wav
002 30 sentences wav wav wav
003 29 sentences wav wav wav
004 29 sentences wav wav wav
005 29 sentences wav wav wav
006 29 sentences wav wav wav
007 29 sentences wav wav wav
008 30 sentences wav wav wav
009 27 sentences wav wav wav
010 29 sentences wav wav wav
028 30 sentences wav wav wav
029 28 sentences wav wav wav
030 27 sentences wav wav wav
031 23 sentences wav wav wav
040 20 sentences wav wav wav
044 28 sentences wav wav wav
047 24 sentences wav wav wav
052 19 sentences wav wav wav
053 16 sentences wav wav wav
054 21 sentences wav wav wav
059 24 sentences wav wav wav
060 29 sentences wav wav wav
061 23 sentences wav wav wav
068 27 sentences wav wav wav
069 29 sentences wav wav wav
070 26 sentences wav wav wav
071 27 sentences wav wav wav
072 28 sentences wav wav wav
073 25 sentences wav wav wav
074 28 sentences wav wav wav
075 25 sentences wav wav wav
076 29 sentences wav wav wav
077 27 sentences wav wav wav
078 23 sentences wav wav wav
079 28 sentences wav wav wav
080 27 sentences wav wav wav
081 26 sentences wav wav wav
082 28 sentences wav wav wav
083 30 sentences wav wav wav
084 28 sentences wav wav wav
085 28 sentences wav wav wav
086 29 sentences wav wav wav
087 26 sentences wav wav wav
088 30 sentences wav wav wav
090 30 sentences wav wav wav
091 30 sentences wav wav wav
092 28 sentences wav wav wav
093 30 sentences wav wav wav
094 26 sentences wav wav wav
095 29 sentences wav wav wav
096 26 sentences wav wav wav
097 30 sentences wav wav wav
098 27 sentences wav wav wav
099 27 sentences wav wav wav


Reference:
Junichi Yamagishi and EMIME members
Coming soon!