Re: evaluation of speech enhancement algorithm. How?

Hi,

You might be able to compare your algorithm with the articulation index
(AI). The result is a scalar value between 0 and 1 (0= speech not
understandable at all, 1=100% speech recognition). In summary, these
models try to predict human speech recognition scores. Which is a
psychoacoutic model of how intelligible speech is given the long term
speech/noise spectrum and the system's response. These, however, like I
said, will require the long term average of your speech (which you
might not be interested in using). There is a free matlab file the
calculates the AI with additional information about it at:

http://server1.cdsp.neu.edu/info/students/hmuesch/

They use non-sense syllable for the estimation. If you signal is speech
you will need to apply a context transformation in the end of it to
compensate for the less entropy.

.

Relevant Pages

  • Re: Dragon NaturallySpeaking and the signal-to-noise ratio number
    ... The malicious misfit Martin Markoe's only USENET activity is spamming ... speech recognition. ... saying a good soundcard does nothing for speech recognition ...
    (comp.speech.users)
  • Re: Dragon NaturallySpeaking and the signal-to-noise ratio number
    ... The malicious misfit Martin Markoe's only USENET activity is spamming ... saying a good soundcard does nothing for speech recognition ...
    (comp.speech.users)
  • Re: 21st Century Speech Recognition
    ... Martin Markoe and Mr. "speaktoyourpc.com", I beg you to consider the ... dealing with you on the newsgroups is not an easy thing and most ... Subject: 21st Century Speech Recognition ...
    (comp.speech.users)
  • Re: Huge document mystery
    ... If you're not using Speech Recognition or Handwriting Recognition, ... Embed linguistic data option. ...
    (microsoft.public.word.newusers)
  • Re: 21st Century Speech Recognition
    ... Martin Markoe and Mr. "speaktoyourpc.com", I beg you to consider the ... dealing with you on the newsgroups is not an easy thing and most ... Subject: 21st Century Speech Recognition ...
    (comp.speech.users)