W3C home > Mailing lists > Public > www-voice@w3.org > January to March 2002

Re: grammar that matches arbitrary word?

From: Jesper Olsen <jolsen@runbox.com>
Date: Tue, 12 Feb 2002 07:42:19 -0500 (EST)
To: www-voice@w3.org
Message-Id: <E16acFr-0006Tq-00@pluto2.runbox.com>
Hi Markku,

Actually that application is not so simple.

Consider what the alternative is
- the recogniser returns a phoneme string *instead* of a word
- the recogniser has a "build in" name grammar

The last option is not really possible - there are two many names in the world
(and new ones are invented all the time).

Besides, is it the name of a person, a company or exactly what?
There could be many other interesting categories.

Your example has 50M words. From an acoustic modeling point of view,
this is quite impossible to handle - the error rate would be too large.

On the whole, I think the <one-of> approach is fine for a simple application. 
VXML was not invented with large vocabulary speech recognition in mind.

Cheers
Jesper


> -----Original Message-----
> From: ext Markku Savela [mailto:msa@msa.tte.vtt.fi]
> Sent: 12 February, 2002 10:11
> To: www-voice@w3.org
> Subject: grammar that matches arbitrary word?
> 
> 
> hi,
> 
> To test my browser, I thougth to write a simple phone directory
> application: ask a name and perfom a query to database.
> 
> However, how do I do this?
> 
> ...
> <field name="name">
>   <prompt>Whose phone number you want to know?</prompt>
>   <grammar>
>    ??? what is the grammar to accept any name ???
>   </grammar>
> </field>
> ...
> 
> Or how this type of application is supposed to be modelled? Although,
> you could generate a grammar from database
> 
>  <one-of>
>   <item> name1 </item>
>   <item> name2 </item>
>   ...
>   ...
>   <item> name589392 </item>
>  <one-of>
> 
> I don't think this a solution...
> 
> 
Received on Tuesday, 12 February 2002 10:40:17 GMT

This archive was generated by hypermail 2.2.0+W3C-0.50 : Monday, 30 October 2006 12:48:54 GMT