The "standalone" version "gnuspeechsa" is the only usable one; original is a mess of ObjC/NeXTSTEP framework stuff. https://ftp.gnu.org/pub/gnu/gnuspeech/ …
-
-
Show this thread
-
Articulatory synth means it models the human vocal tract (albeit primitively) rather than pasting together recorded phoneme clusters.
Show this thread -
Wow @ this sample produced with gnuspeech: http://pages.cpsc.ucalgary.ca/~hill/extra-synthesis-examples/pat-a-pan.html …
Show this thread
End of conversation
New conversation -
-
-
http://www.cstr.ed.ac.uk/projects/festival/ … produced decent output when I looked at it a couple of decades ago.
-
The architecture behind festival is hideous. Flite much less so, but it still doesn't seem to be aimed at doing anything practical OR at facilitating experimentation.
End of conversation
New conversation -
-
-
FWIW: I messed around with implementing speech synthesis before, but didn't get great results at the time regarding intelligibility. I guess I could experiment more with this again if anyone might be interested.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
julius seemed the most promising for F/OSS speech-to-text. Alas, public versions had only been trained on 日本語 lexicons though some private English ones existed apparently. CMUSphinx was not so nice circa 2008/2009 when I was last exploring such code bases much.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.