I suspect this will be very similar in implementation to switch_core_asr, so we could either reuse that interface, or implement a new Speaker Identification and Verification (SIV) interface. Hop on #freeswitch-dev to talk this over and figure out the best approach.<br>
<br>If you implement a new interface, you probably need at least the following functions:<br><br>switch_core_siv_open<br>switch_core_siv_close<br>switch_core_siv_pause<br>switch_core_siv_resume<br>switch_core_siv_feed<br>
switch_core_siv_get_results<br>switch_core_siv_start_input_timers<br><br>And then some new functions in switch_ivr_async.c:<br><br>switch_ivr_detect_speaker<br>switch_ivr_pause_detect_speaker<br>switch_ivr_resume_detect_speaker<br>
switch_ivr_stop_detect_speaker<br>switch_ivr_detect_speaker_start_input_timers<br><br>And a new application in mod_dptools.c<br><br>detect_speaker<br><br><br><br><div class="gmail_quote">On Thu, Aug 18, 2011 at 8:35 AM, Viktor Jamrich <span dir="ltr"><<a href="mailto:viktor_jamrich@centrum.sk">viktor_jamrich@centrum.sk</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">That's it ! I was talking about speaker identification by comparing the<br>
speaker's voiceprint with<br>
pre-trained voiceprint saved in a voiceprint repository. Sure, I've<br>
heard about Nuance is planning to acquire<br>
Loquendo, another speech processing shark ;)<br>
<br>
I was thinking about creating a new abstract interface called e.g.<br>
switch_sid_interface (SID = speaker identification) which<br>
could be binded to e.g. a proprietary interface module or (the better<br>
solution) to mod_unimrcp since MRCPv2 protocol supports<br>
speaker identification/verification. Using this sid interface w/<br>
mod_unimrcp FreeSWITCH would be able to use MRCP<br>
servers for speaker identification/verification. Currently Nuance and<br>
Loquendo has few MRCP servers supporting this service and<br>
of course our company is planning to deploy a MRCPv2 server soon.<br>
Example application is e.g. instead of looking for your customer<br>
ID or telling your personal ID data to the operator who needs to have<br>
your identity confirmed before he/she tells you some confidental info,<br>
the company (whether call center or whatever) would just use speaker<br>
identification service via MRCPv2 and from 3 to 5 seconds of voice<br>
he/she will know, whether the person is really the one he/she is<br>
claiming he/she is or not.<br>
<br>
What do you think about it ??<br>
<br>
Have a nice day ;)<br>
<br>
Sincerely, Viktor Jamrich.<br>
<br>
_______________________________________________<br>
Join us at ClueCon 2011, Aug 9-11, Chicago<br>
<a href="http://www.cluecon.com" target="_blank">http://www.cluecon.com</a> 877-7-4ACLUE<br>
<br>
FreeSWITCH-dev mailing list<br>
<a href="mailto:FreeSWITCH-dev@lists.freeswitch.org">FreeSWITCH-dev@lists.freeswitch.org</a><br>
<a href="http://lists.freeswitch.org/mailman/listinfo/freeswitch-dev" target="_blank">http://lists.freeswitch.org/mailman/listinfo/freeswitch-dev</a><br>
UNSUBSCRIBE:<a href="http://lists.freeswitch.org/mailman/options/freeswitch-dev" target="_blank">http://lists.freeswitch.org/mailman/options/freeswitch-dev</a><br>
<a href="http://www.freeswitch.org" target="_blank">http://www.freeswitch.org</a><br>
</blockquote></div><br>