Après
SyntheseParole,
WebCam toussa... voir
http://cookerspot.tuxfamily.org/wikka.php?wakka=ReconnaissanceVocale qui est un peu mieux organisé
- http://freshmeat.net/projects/julius-lvcsr/
- Julius is a high-performance large vocabulary continuous speech recognition (LVCSR) engine for speech-related research and development. You can construct your own speech recognition system, but you need a separate English acoustic model and language model or grammar file.
- mis à jour en janvier 2007 (release 3.5.3)
un jour yaura
ReconnaissanceEcriture? mais pour l'instant :