festvox-rms-arctic-hts - US English male speaker "RMS" for Festival
| Website: | http://www.cstr.ed.ac.uk/projects/festival/ |
|---|---|
| License: | MIT and GPL+ and TCL |
| Vendor: | Fedora Project |
- Description:
US English male speaker ("RMS") voice for Festival. This is a HMM-based Speech Synthesis System (HTS) voice from the Nagoya Institute of Technology, trained using the CMU ARCTIC database. This voice is based on 1132 utterances spoken by a US English male speaker. The speaker is experienced in building synthetic voices. This was recorded at 16bit 32KHz, in a sound proof room, in stereo, one channel was the waveform, the other EGG. The database was automatically labelled using EHMM an HMM labeler that is included in the FestVox distribution. No hand correction has been made.
Packages
| festvox-rms-arctic-hts-0.20061229-11.fc11.noarch [1.5 MiB] |
Changelog
by Jesse Keating (2009-03-24):
- Drop the explicit dep on festival-voice, as it is redundant and causes problems with multiple providers |