<html>
<head>
<style>
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
FONT-SIZE: 10pt;
FONT-FAMILY:Tahoma
}
</style>
</head>
<body class='hmmessage'>
<BR>
Thanks for the answer Stephen, I have install ABE with 7.1 engine. In many times I make a question about the engine 7.5 for ABE, Do you have a release of engine 7.5 for ABE??<BR>
<BR>
Thank you.<BR>
Regards!!<BR><BR><BR>
> Date: Wed, 29 Aug 2007 08:51:06 -0700<BR>> From: StephenKeller@LumenVox.com<BR>> To: asterisk-speech-rec@lists.digium.com<BR>> Subject: Re: [asterisk-speech-rec] Min-Max Value Lumenvox Parameters<BR>> <BR>> <BR>> Hector Lopez wrote:<BR>> <BR>> > Would you tell me the minimal and maximun values for parameters in<BR>> lumevox.cof<BR>> <BR>> Actually, the parameters you're looking at are outdated, Hector. The<BR>> current version of the Engine (7.5.600) and above, when used with b16<BR>> and above of the connector bridge, support some new parameters.<BR>> <BR>> I've copied over the contents of the new lumenvox.conf supplied with the<BR>> current connector bridge, which has some comments that are hopefully<BR>> more clear as to what each parameter does and how it can be set.<BR>> <BR>> One thing worth noting is that snr_sensitivity and volume_sensitivity<BR>> are both set on scales from 0-100; I don't think most of the other<BR>> parameters have maximum values, as they are all time settings (but you<BR>> wouldn't want to set them very high).<BR>> <BR>> Check out<BR>> http://www.lumenvox.com/helpProxy/index.aspx?project=speechengine&id=756<BR>> for information about the sensitivity settings.<BR>> <BR>> We also have some recommended parameters at<BR>> http://www.lumenvox.com/helpProxy/index.aspx?project=speechengine&id=680<BR>> <BR>> So basically I suggest you go to http://www.lumenvox.com/customers/ and<BR>> log in, grab the latest connector bridge and Engine, and install those<BR>> before you spend too much time tweaking the older parameters. The newer<BR>> VAD works much better is much easier to set.<BR>> <BR>> ; Signal-to-noise sensitivty<BR>> ; Determines how much louder the speaker must be than the background<BR>> noise in<BR>> ; order to trigger barge-in. The smaller this value, the easier it will <BR>> ; be to trigger barge-in.<BR>> vad_snr_sensitivity=50<BR>> <BR>> ; Volume sensitivity<BR>> ; The volume required to trigger barge-in. The smaller the value, the<BR>> more <BR>> ; sensitive barge-in will be. This is primarily used to deal with poor<BR>> echo <BR>> ; cancellation. By setting this value higher (less sensitive) prompts<BR>> that are<BR>> ; not properly cancelled will be less likely to falsely cancel barge-in.<BR>> vad_volume_sensitivity=50<BR>> <BR>> ; End-of-speech delay <BR>> ; This is the amount of time, specified in milliseconds, that the <BR>> ; Engine must detect silence after speech before it begins processing <BR>> ; the utterance. Set this value lower to capture short utterances such<BR>> as<BR>> ; single words. Set it lower for longer utterances that are likely to<BR>> have many<BR>> ; pauses in between speech, such as long digit strings.<BR>> vad_eos_delay=1250<BR>> <BR>> ; Wind-back length<BR>> ; The length of audio to be wound back at the beginning of voice<BR>> activity. This<BR>> ; is used primarily to counter instances where barge-in does not<BR>> accurately <BR>> ; capture the very start of speech. The resolution of this parameter <BR>> ; is 1/8 of a second.<BR>> vad_wind_back=750<BR>> <BR>> ; End of speech timeout<BR>> ; This is the total amount of time to listen for speech after barge-in<BR>> has <BR>> ; been detected. This differs from the end-of-speech timeout as this is<BR>> ; the total time a speaker has to speak, not the length of time between <BR>> ; individual words. This parameter should not usually need to be<BR>> changed.<BR>> end_of_speech_timeout=15000<BR>> <BR>> <BR>> Thanks,<BR>> <BR>> Stephen Keller<BR>> LumenVox Support<BR>> P: 877-977-0707, just say "Support"<BR>> F: 858-707-7072<BR>> Support@LumenVox.com<BR>> www.LumenVox.com <http://www.lumenvox.com/> <BR>> <BR>> <http://www.lumenvox.com/> <BR>> <BR>> Winner "Best Innovation in Speech Recognition"<BR>> AVIOS SpeechTEK Award<BR>> <BR>> <BR>> <BR>> _______________________________________________<BR>> --Bandwidth and Colocation Provided by http://www.api-digital.com--<BR>> <BR>> asterisk-speech-rec mailing list<BR>> To UNSUBSCRIBE or update options visit:<BR>> http://lists.digium.com/mailman/listinfo/asterisk-speech-rec<BR><BR><br /><hr />Con Windows Live Spaces en Prodigy/MSN abre tu mundo y crea tu propio espacio. <a href='http://spaces.live.com/' target='_new'>Es gratis</a></body>
</html>