[linux-audio-dev] Speech analysis

Jack O'Quin joq at io.com
Mon Jun 6 16:38:47 UTC 2005


Susan Cragin <susancragin at earthlink.net> writes:

> Hi. I'm a lurker from the Open-Source Speech Recognition Initiative.

Welcome.  Interesting topic.

> We are starting to collect voice samples and need an audio program
> that can segment speech by word, or attempt to, by recognizinig all
> the silences and placing markers at each location.

I don't really know much about this, but my impression is that real
speech doesn't usually *have* silence between words.  The words all
run together within a sentence.

There's bound to be lots of literature on this subject.  My guess is
you'll need to scan for phonemes first, then find the word boundaries
based on that analysis.  Probably some people on this list will have
some useful experience.

Good luck!
-- 
  joq



More information about the Linux-audio-dev mailing list