|
From: Chris A. <ro...@gm...> - 2015-05-15 10:28:10
|
On Fri, May 15, 2015 at 8:24 PM, Rafal Maszkowski <rz...@ic...> wrote: > On Sun, Dec 28, 2014 at 01:33:12PM +0100, Jan Stary wrote: >> On Dec 23 20:34:42, 4-...@gm... wrote: >> > The project I am trying to build is a speech to text system. >> > The system as 2 parts: first a sox filter to convert the mic input into >> > a binary file with a.. .txt label. The. .txt file is the in put to >> > another beautiful and free program called chatscript. >> Does that mean you want the *.txt file to be a text transcript of the speech >> that comes through the mic? SoX cannot do anything like that. > > I thing that SoX can make a step in that direction by implementing > MPEG-7. But it still would be quite far away from speech recognition. > Anyway if there are no volunteers even this step cannot be done yet. Not sure MPEG-7 would really help - that's like saying "I have a UTF-8 codec, that means I can write a letter in Russian". Out of interest, though, what _would_ you recommend for doing basic software transcription of audio? There seem to be a lot of options around, most of them either pay-for or low quality. ChrisA |