Diverse speakers' HTS voices trained on non-speech synthesis corpora:
Audio Examples
Wall street journal 0 (WSJ0)
Robust speaker-adaptive speech synthesis system 'HTS-2007'
Male speakers
| Speaker's ID | Number of adaptation sentences | Utterance 1 | Utterance 2 | Utterance 3 |
| 20c | 91 sentences | wav | wav | wav | 20f | 91 sentences | wav | wav | wav | 20g | 91 sentences | wav | wav | wav | 20i | 90 sentences | wav | wav | wav | 20j | 65 sentences | wav | wav | wav | 20k | 90 sentences | wav | wav | wav | 20l | 92 sentences | wav | wav | wav | 20m | 93 sentences | wav | wav | wav | 20n | 92 sentences | wav | wav | wav | 20o | 91 sentences | wav | wav | wav | 20q | 91 sentences | wav | wav | wav | 20r | 99 sentences | wav | wav | wav | 20s | 92 sentences | wav | wav | wav | 20v | 92 sentences | wav | wav | wav | 207 | 92 sentences | wav | wav | wav | 208 | 92 sentences | wav | wav | wav | 012 | 130 sentences | wav | wav | wav | 013 | 142 sentences | wav | wav | wav | 015 | 140 sentences | wav | wav | wav | 01e | 141 sentences | wav | wav | wav | 01g | 142 sentences | wav | wav | wav | 01l | 142 sentences | wav | wav | wav | 01r | 141 sentences | wav | wav | wav | 01s | 140 sentences | wav | wav | wav | 01t | 144 sentences | wav | wav | wav | 01w | 140 sentences | wav | wav | wav | 01y | 140 sentences | wav | wav | wav | 01z | 143 sentences | wav | wav | wav | 020 | 141 sentences | wav | wav | wav | 021 | 142 sentences | wav | wav | wav | 024 | 141 sentences | wav | wav | wav | 025 | 141 sentences | wav | wav | wav | 026 | 140 sentences | wav | wav | wav | 029 | 143 sentences | wav | wav | wav | 02b | 142 sentences | wav | wav | wav | 40a | 141 sentences | wav | wav | wav | 40b | 138 sentences | wav | wav | wav | 40c | 142 sentences | wav | wav | wav | 40f | 144 sentences | wav | wav | wav | 40i | 140 sentences | wav | wav | wav | 40j | 141 sentences | wav | wav | wav | 40k | 140 sentences | wav | wav | wav | 40n | 141 sentences | wav | wav | wav | 403 | 138 sentences | wav | wav | wav | 405 | 142 sentences | wav | wav | wav | 406 | 140 sentences | wav | wav | wav | 408 | 141 sentences | wav | wav | wav | 051 | 182 sentences | wav | wav | wav | 052 | 183 sentences | wav | wav | wav | 22g | 197 sentences | wav | wav | wav | 422 | 363 sentences | wav | wav | wav | 423 | 360 sentences | wav | wav | wav | 00b | 794 sentences | wav | wav | wav | 00c | 779 sentences | wav | wav | wav | 00d | 795 sentences | wav | wav | wav | 431 | 962 sentences | wav | wav | wav |
| 001 | 100 sentences | wav | wav | wav |
| 001 | 1000 sentences | wav | wav | wav |
| 001 | 2000 sentences | wav | wav | wav | 59 males' average voice | --- | wav | wav | wav |
movie
Female speakers
| Speaker's ID | Number of adaptation sentences | Utterance 1 | Utterance 2 | Utterance 3 |
| 204 | 91 sentences | wav | wav | wav |
| 205 | 92 sentences | wav | wav | wav |
| 01n | 103 sentences | wav | wav | wav |
| 011 | 141 sentences | wav | wav | wav |
| 014 | 142 sentences | wav | wav | wav |
| 016 | 141 sentences | wav | wav | wav |
| 017 | 142 sentences | wav | wav | wav |
| 018 | 140 sentences | wav | wav | wav |
| 019 | 140 sentences | wav | wav | wav |
| 01a | 142 sentences | wav | wav | wav |
| 01b | 139 sentences | wav | wav | wav |
| 01c | 141 sentences | wav | wav | wav |
| 01d | 142 sentences | wav | wav | wav |
| 01f | 138 sentences | wav | wav | wav |
| 01j | 140 sentences | wav | wav | wav |
| 01k | 142 sentences | wav | wav | wav |
| 01m | 141 sentences | wav | wav | wav |
| 01o | 141 sentences | wav | wav | wav |
| 01p | 140 sentences | wav | wav | wav |
| 01q | 142 sentences | wav | wav | wav |
| 01u | 141 sentences | wav | wav | wav |
| 01v | 140 sentences | wav | wav | wav |
| 01x | 141 sentences | wav | wav | wav |
| 022 | 142 sentences | wav | wav | wav |
| 023 | 140 sentences | wav | wav | wav |
| 027 | 140 sentences | wav | wav | wav |
| 028 | 140 sentences | wav | wav | wav |
| 02a | 138 sentences | wav | wav | wav |
| 02c | 141 sentences | wav | wav | wav |
| 02d | 140 sentences | wav | wav | wav |
| 02e | 142 sentences | wav | wav | wav |
| 401 | 139 sentences | wav | wav | wav |
| 404 | 140 sentences | wav | wav | wav |
| 407 | 140 sentences | wav | wav | wav |
| 409 | 141 sentences | wav | wav | wav |
| 40d | 141 sentences | wav | wav | wav |
| 40e | 140 sentences | wav | wav | wav |
| 40g | 141 sentences | wav | wav | wav |
| 40h | 140 sentences | wav | wav | wav |
| 40l | 143 sentences | wav | wav | wav |
| 40m | 141 sentences | wav | wav | wav |
| 40o | 142 sentences | wav | wav | wav |
| 40p | 141 sentences | wav | wav | wav |
| 420 | 360 sentences | wav | wav | wav |
| 421 | 360 sentences | wav | wav | wav |
| 00a | 801 sentences | wav | wav | wav |
| 00f | 792 sentences | wav | wav | wav |
| 430 | 966 sentences | wav | wav | wav |
| 432 | 960 sentences | wav | wav | wav |
| 002 | 100 sentences | wav | wav | wav |
| 002 | 1000 sentences | wav | wav | wav |
| 002 | 2000 sentences | wav | wav | wav | 60 females' average voice | --- | wav | wav | wav |
Speaker-dependent speech synthesis system 'HTS-Nitech 2005 / HTS-Benchmark'
| Speaker's ID | Number of adaptation sentences | Utterance 1 | Utterance 2 | Utterance 3 |
| 001 | 2534 sentences | wav | wav | wav |
| 002 | 2540 sentences | wav | wav | wav |
| 400 | 2713 sentences | wav | wav | wav |
- Reference:
- Bela Usabaev Junichi Yamagishi, Simon King
Coming soon!