Changeset 2637 for Trunk/Scripts/Audio_scripts/AudioSegmentation
- Timestamp:
- 08/27/08 10:42:17 (5 months ago)
- Files:
Legend:
- Unmodified
- Added
- Removed
- Modified
- Copied
- Moved
Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook.pm
r2636 r2637 29 29 $./AudioBook -h display help 30 30 $./AudioBook -a speechfile.wav -t text.txt minimal run configuration 31 32 =head1 REQUIREMENTS 33 34 =item 1 - Sequitor G2P trainable Grapheme-to-Phoneme converter (GPL v2; requires Python to be installed) 35 36 http://www-i6.informatik.rwth-aachen.de/web/Software/g2p.html 37 38 =item 2 - HTK Hidden Markov Model Toolkit (note: the source is "open" - i.e. you can read the code - but there are distribution restrictions) 39 40 http://htk.eng.cam.ac.uk/ 41 42 The HTK toolkit needs to be in your path 43 (see http://www.voxforge.org/home/dev/acousticmodels/linux/create/htkjulius/tutorial/download) 44 45 =item 3 - Perl packages 46 47 Term::ReadLine::Gnu 48 Audio::Wav 49 Lingua::EN::Numbers 50 XML::LibXML 51 File::Copy 31 52 32 53 =head1 DESCRIPTION … … 226 247 and compared with the pronunications generated by Sequitor, and a judgment call needs to be made to select the correct pronunciations. 227 248 228 =head1 REQUIREMENTS 229 230 =item 1 - Sequitor G2P trainable Grapheme-to-Phoneme converter (GPL v2; requires Python to be installed) 231 232 http://www-i6.informatik.rwth-aachen.de/web/Software/g2p.html 233 234 =item 2 - HTK Hidden Markov Model Toolkit (note: the source is "open" - i.e. you can read the code - but there are distribution restrictions) 235 236 http://htk.eng.cam.ac.uk/ 237 238 The HTK toolkit needs to be in your path 239 (see http://www.voxforge.org/home/dev/acousticmodels/linux/create/htkjulius/tutorial/download) 240 241 =item 3 - Perl packages 242 243 Term::ReadLine::Gnu 244 Audio::Wav 245 Lingua::EN::Numbers 246 XML::LibXML 247 File::Copy 248 249 =cut 249 =cut 250 250 251 251 ####################################################################