Re: Comparison of 2 'wav' files

Tech-Archive recommends: Repair Windows Errors & Optimize Windows Performance

Any advice?

"HuaMin" wrote:

Thanks Chris. I do expect to store the sound file of every one word of a
phrase, and further to validate/detect the sound of the words from the speech
against the stored sound files. Is there any example for this?

"Chris P." wrote:

On Thu, 9 Jul 2009 21:12:01 -0700, HuaMin wrote:

I've checked that, one product from that is 'Dragon Naturally speaking'. As
its technical support does need a valid registry key, I can't use that
service. Do you know which product actually is for comparing 2 sounds.

How about the idea to store a sound like a sequence of sme stuff?

Are you comparing sounds or voices? Are you trying to authenticate the
voice or match it to a phrase?

If you are comparing speech phrases, then comparing sounds is not enough.
You have to break the speech down into phonemes and then compare this to
what you've stored.

If you are voice printing for speaker identification then this is a whole
different challenge. This requires recognizing the high frequency
variations in signal.

Nuance has products that do both of these tasks, you will have to contact
their sales to get evaluation software.

--
http://www.chrisnet.net/code.htm
[MS MVP for DirectShow / MediaFoundation]

.

Relevant Pages

  • Re: Sound Identification/Matching - good starting point?
    ... Sound Identification/Matching? ... start matching up sounds that way by comparing snapshots taken from ... Address as compared to a sneeze or a sneeze as compared to a phrase "help ... Speech Recognition) for Linux." ...
    (comp.dsp)
  • Re: Why do you like Mozarts music?
    ... >> someone really wants to make a claim for a specific speech dialect ... > and many German composers write themes which reflect the phrase ... > sentence I am writing now, and there are a lot of examples for this ... evoke speech rhythms, for you, but I hope you see that there is no ...
    (rec.music.classical.recordings)
  • Re: Question for John Atkinson
    ... >> the testee can't see as well as the differences in the level of sound ... > be comparing things that he has a natural prefernce for. ... >>> that if one is not looking for improvement there is no reason to do a DBT. ... Remember that it cannot be base on SPL and preferences. ...
    (rec.audio.opinion)
  • Re: A reasonable argument against double blind tests?
    ... I do think however, that one can do a decent job of comparing by just arranging speaker pairs AB/AB style, with one item of each pair to the left of each item of the second pair. ... the AB/AB arrangement is still problematical when comparing speakers designed for close to front wall placement with those designed to be located well out from that wall. ... A good speaker might sound good with a really good recording and a poor speaker might not sound so good. ... However, the latter might sound decent with some kind of souped-up, weirdly mastered recording and the good speaker might sound bad, because it was accurately reproducing the defects in the recording Yep, speakers are tricky to evaluate. ...
    (rec.audio.opinion)
  • Re: Why do you like Mozarts music?
    ... >>> someone really wants to make a claim for a specific speech dialect ... > good measure, the language he actually spoke, Swedish. ... >> sentence I am writing now, and there are a lot of examples for this ... Beethoven does write complex phrase structures (known obligingly ...
    (rec.music.classical.recordings)