W3C home > Mailing lists > Public > www-voice@w3.org > October to December 2007

Re: Confidence Scoring Weirdness

From: Shane Smith <safarishane@gmail.com>
Date: Thu, 1 Nov 2007 23:47:59 -0700
Message-ID: <8fc15e140711012347s72c07fc9k49e7be6c47799ac0@mail.gmail.com>
To: "Ian Sutherland" <ian.sutherland@oracle.com>
Cc: "Andrew Hunt" <andrew.hunt@holly.com.au>, "Robert Stewart" <robert@wombatnation.com>, www-voice@w3.org
Maybe we need a application.lastResult.$ambiguity scoring system as well.

On 11/1/07, Ian Sutherland <ian.sutherland@oracle.com> wrote:
>
> Andrew Hunt wrote:
> > One approach is that the score
> > reflects the "acoustic match"
>
> [...]
>
> > Another approach tries to
> > determine how likely the guess is to be correct
>
> [...]
>
> > There are many other variations
> > and many bright people have spent good time debating the relative merits
> >
>
> If there are multiple different notions of confidence, shouldn't there
> be multiple different "confidence" scores in VoiceXML?  Is there at
> least some core set of confidence measures that one could settle on and
> make into different "confidence" properties?
>
>
Received on Friday, 2 November 2007 06:48:07 GMT

This archive was generated by hypermail 2.2.0+W3C-0.50 : Friday, 2 November 2007 06:48:20 GMT