[asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software?

[Jeff LaCoursiere]

This would work if you only care that you get very rough phonetic 
spellings as Don implied.  If you think about it humans cannot do any 
better.  I know personally - I have to spell my name all the time. 
Perhaps your app could ask them to spell their name,  which actually has a 
shot at reliability of not useability.

j

On Sat, 31 Jan 2009, Kurian Thayil wrote:

> Hi Alfred,
>
> There is a research project by Carnegie Mellon University (CMU) on a very
> versatile Speech Recognition Software. Its Sphinx
> http://cmusphinx.sourceforge.net/html/cmusphinx.php . This application is in
> raw state and the Version 2 of sphinx could be integrated with Asterisk.
> Festival (Text to Speech application) that is widely used in asterisk is by
> CMU. Refer http://www.voip-info.org/wiki-Sphinx . I hope this gives a pretty
> good start.
>
> Sphinx needs to be trained with a language model. But since your requirement
> is just names it should not be complicated. Also have a look at
> http://www.speech.cs.cmu.edu/Communicator/ . Something I have not looked
> into much (and I don't know if it has anything to do with Asterisk). I hope
> this helps.
>
> Regards,
>
> Kurian Thayil.
>
>
> On Sat, Jan 31, 2009 at 9:22 AM, Alfred Monticello <ajmcello at yahoo.com>wrote:
>
>>
>> I wouldn't have a database to compare names to, each one would essentially
>> be unique and unknown. It's sounding like this idea may be not
>> possible...What high end options are available? I read about lumenvox, but I
>> believe that compares to a known list of names (such as a directory, or Yes
>> No, Digits, etc)....
>>
>> Hum...
>>
>>
>> ------------------------------
>> *From:* Don Kelly <dk at donkelly.biz>
>> *To:* Asterisk Users Mailing List - Non-Commercial Discussion <
>> asterisk-users at lists.digium.com>
>> *Sent:* Friday, January 30, 2009 7:41:02 PM
>> *Subject:* Re: [asterisk-users] Ideas on how to convert spoken name to
>> text (orwav to text)..speech recognition software?
>>
>>  There are solutions ranging from free to many thousands of dollars, with
>> effectiveness ranging from nearly worthless to almost pretty good.
>>
>>
>>
>> A lot depends on your application.
>>
>>
>>
>> The most successful application would match an utterance from a known
>> speaker to a known list of a couple dozen names. For example, if I say
>> "Alfred Monticello," the application can easily distinguish this from other
>> list entries such as "Don Kelly" and "Robert Smith."
>>
>>
>>
>> The least successful would attempt to convert an utterance from an unknown
>> speaker to text (which is what your inquiry implies). Even if it clearly
>> "understands" the speaker, the result could easily be "Alphret Mahntichelo."
>>
>>   --Don
>>
>> Don Kelly
>> PCF Corp
>> People Come First
>>
>> 651 842-1000
>> 888 Don Kell(y)
>> 651 842-1001 fax
>>   ------------------------------
>>
>> *From:* asterisk-users-bounces at lists.digium.com [mailto:
>> asterisk-users-bounces at lists.digium.com] *On Behalf Of *Alfred Monticello
>> *Sent:* Friday, January 30, 2009 9:25 PM
>> *To:* asterisk-users at lists.digium.com
>> *Subject:* [asterisk-users] Ideas on how to convert spoken name to text
>> (orwav to text)..speech recognition software?
>>
>>
>>
>>
>>
>> I'm interested in taking a persons spoken recorded name (First, Last) and
>> converting the two spoken words to text. Is there any solutions out there
>> that would make this possible?
>>
>>
>>
>>
>> _______________________________________________
>> -- Bandwidth and Colocation Provided by http://www.api-digital.com --
>>
>> asterisk-users mailing list
>> To UNSUBSCRIBE or update options visit:
>>   http://lists.digium.com/mailman/listinfo/asterisk-users
>>
>