similar to: Losing first DTMF digit (with ASR)

Which speed recognition products will also recognize DTMF? In other words, I want to say "Please speak or dial the conference number". Does Vestec allow that? LumenVox? Any other way?

I'm using QSIG between Asterisk and an NEC SV8300. Whenever I make a call from the SV8300, I see: [Oct 4 21:02:49] ERROR[5729]: chan_dahdi.c:12226 dahdi_pri_error: !! < Unknown IE 50 (cs5, len = 3) I see an IE 50 in the Q.932 specification, so I don't understand why this error is occuring.

Hi there, I am using Asterisk 11.9 (with Sangoma-E1-Card/DAHDI) and it works fine :-) But I am wondering if there is a solution/application which will enable me to implement voice recognition while playing a voice file (barge in). So that the caller hears a voice file and can interrupt it with his voice. Currently (on our platform) the caller has to wait for the end of the voicefie. Then we play

I just updated libpri 1.4 on my system to the latest from that branch and my QSIG connection to an NEC SV8300 stopped working. The trace showing the problem is below: q931.c:5640 q931_connect: Call 7168 enters state 10 (Active). Hold state: Idle > DL-DATA request > Protocol Discriminator: Q.931 (8) len=21 > TEI=0 Call Ref: len= 2 (reference 7168/0x1C00) (Sent to originator) >

I'm having a lot of problem with it recognizing "oh" for zero. I've tried both "o" and "oh". In one case, I just tried: $digit = o { out = "0"; } | fundamental {out = "2"; }; So I gave it a choice that was VERY far away from what I said. But when I said "o o o o o", more than 75% of the time, it had a bunch of

Hi, We've run into an interesting (to us) problem with SpeechBackground. Inside a AGI script, we're playing some extended audio?basically, like a podcast?and we want playback to stop if and only if the speech recognized matches something in our grammar. If there's speech that doesn't match, we just want to go right on playing. (We're using LumenVox as our speech recognition

Is this patch correct? The "&&" doesn't make logical sense to me. I think it should be "||" and making this change fixes the problem I have with SIP phones in MeetMe conferences. If it's correct, is there someplace more formal that I should submit it to? *** app_meetme.c.old 2009-10-11 17:56:44.000000000 -0400 --- app_meetme.c 2009-10-17

It appears that there are no transcoders from g723 to anything else in Asterisk 10.7.1. Does anybody know how to fix that?

I'm confused exactly what's supported with LDAP and Asterisk. What I want to do is to have SIP peer information read directly (in realtime) from LDAP. Can this be done? If so, with what Asterisk versions?

> CALLERID is a read only variable. That's not correct. I set it all over the place in my dialplan.

Interesting. Are you using the included cbend.php script to terminate conferences? I occasionally get questions about using WMM with Confbridge, and to date I have not had an answer . If you can provide details, even vague ones, about how you did it, I can update the WMM package. Dan -----Original Message----- From: asterisk-users-bounces at lists.digium.com [mailto:asterisk-users-bounces at

Hi, This is a naive question, but is there a way in my AGI script to simultaneously play audio and listen for DTMF or voice responses? I've heard VOIP hackers call this "inbargeability;" it's the ability to "barge in" to a playing audio clip. I'm planning to use Lumenvox for the DTMF and voice recognition, BTW. Not sure if that matters. Many thanks to anyone who

It's kind of low for me. How does one control that volume?

Is it correct that the unimrcp is the best approach for Asterisk and ASR/TTS? Could anyone provide pros/cons for the various ASR options for Asterisk? We need the ability for very large grammars (over 100,000 options). Because of this, my initial thought is Nuance or Lumenvox. Does this sound correct? Have a great day! Dan -------------- next part -------------- An HTML attachment was

Hello, Question for developers: what is the asterisk way to integrate with ASR (speech recognition)? Question to the community: has someone done anything in this direction? On the first glance that shouldn't be too hard. One part is delivering audio to the engine (for example, main ASR players Nuance and Speechworks will be happy with RTP) - can be done via RTP forking. The other part is

Hello, All of the Opus quality studies that I've seen focused on human-perceived quality. I'm interested to know of any experience with machined "perceived" quality, particularly related to speech recognition or biometrics. I'm also interested in folks thoughts on optimizing Opus for ASR. For example, removing certain classes of comfort noise, filtering non-speech bands,

Is there any program Asterisk users use to calculate ASR and ACD ?? Thanks for any comments. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://lists.digium.com/pipermail/asterisk-users/attachments/20090910/af1f9656/attachment.htm

Is there a ready add-on to asterisk that will display the ACD/ASR per channel, source & destination? Thanks. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://lists.digium.com/pipermail/asterisk-users/attachments/20091014/48076c6b/attachment.htm

Greetings list, I am working on a project on which we wish to use Speex with Google Automatic Speech Recognition (ASR) to transcribe Speex audio being sent on to Google ASR service and return us the text of the spoken audio in the Speex audio stream. However, Google ASR's Speex support requires the off-standard Speex-with-header-byte format, and my group cannot find any worthwhile

Hello, I have been working on designs for two different projects, where both of them would need to use the IBM Watson streaming ASR service. Based on our discussion at AstriDevCon, I know there is currently no support for that. However, there may be some workarounds I am not aware of. Would it be possible to write out the audio frames as they get recorded? Watson supports 16 bit signed little