<table cellspacing="0" cellpadding="0" border="0" ><tr><td valign="top" style="font: inherit;">Hi Hector,<br><br>the point with Dragon Speak is that it already has a language model buil-in (and an acoustic model as well). It's not just an ASR engine. <br><br>To solve your problem, you must have an ASR engine + statistical language model (LM) + acoustic model (AM). These three parts together can be called ASR system and it can be built directly from entreprises like Nuance and Loquendo. But if you want to use a free ASR system you'll have to combine a free engine + a free statistical LM + a free AM.<br><br>Two known free engines are Sphinx and Julius. I think that you can find some free english LMs and english AMs supported by these engines at http://www.voxforge.org/ and http://www.keithv.com/software/.<br><br>One problem that you'll face with these free engines is the lack of MRCP support. But it can be easily solved just by writing a simple module in
FS (for example, see mod_pocketsphinx.c that comes with the source code of FS).<br><br>I hope it helps ...<br>Eduardo<br><br><br>--- Em <b>qua, 22/6/11, Hector Geraldino <i><Hector.Geraldino@ip-soft.net></i></b> escreveu:<br><blockquote style="border-left: 2px solid rgb(16, 16, 255); margin-left: 5px; padding-left: 5px;"><br>De: Hector Geraldino <Hector.Geraldino@ip-soft.net><br>Assunto: [Freeswitch-users] FS and ASR engine<br>Para: "FreeSWITCH Users Help" <freeswitch-users@lists.freeswitch.org><br>Data: Quarta-feira, 22 de Junho de 2011, 11:54<br><br><div id="yiv347085808"><style><!--
#yiv347085808
_filtered #yiv347085808 {font-family:Calibri;panose-1:2 15 5 2 2 2 4 3 2 4;}
#yiv347085808
#yiv347085808 p.yiv347085808MsoNormal, #yiv347085808 li.yiv347085808MsoNormal, #yiv347085808 div.yiv347085808MsoNormal
{margin:0in;margin-bottom:.0001pt;font-size:11.0pt;font-family:"sans-serif";}
#yiv347085808 a:link, #yiv347085808 span.yiv347085808MsoHyperlink
{color:blue;text-decoration:underline;}
#yiv347085808 a:visited, #yiv347085808 span.yiv347085808MsoHyperlinkFollowed
{color:purple;text-decoration:underline;}
#yiv347085808 span.yiv347085808EmailStyle17
{font-family:"sans-serif";color:windowtext;}
#yiv347085808 .yiv347085808MsoChpDefault
{}
_filtered #yiv347085808 {margin:1.0in 1.0in 1.0in 1.0in;}
#yiv347085808 div.yiv347085808WordSection1
{}
--></style><div class="yiv347085808WordSection1"><p class="yiv347085808MsoNormal">Hi everyone,</p><p class="yiv347085808MsoNormal"> </p><p class="yiv347085808MsoNormal">I want to check with you guys to see if anyone has experience integrating FreeSwitch with an ASR engine, and using the engine as a merely transcriber of the conversation. </p><p class="yiv347085808MsoNormal"> </p><p class="yiv347085808MsoNormal">I’ve been playing for the past two weeks or so with Nuance Speech Server/recognizer and pocketsphinx. Nuance is by far a better solution, but due to the lack of freely available documentation and my short expertise in this subject, I haven’t been to achieve my goal.</p><p class="yiv347085808MsoNormal"> </p><p class="yiv347085808MsoNormal">The communication between FS and the ASR engine works great using MCRP, my concern is with the ASR engine itself. I want to allow the user to speak freely, and get a transcription of what
the user said. I don’t want or need to understand what the meaning of the utterances are (definitely the engine doesn’t need to do that), also I don’t need/want to write any complex grammar or SLM to get an interpretation of the spoken phrases, I just want the plain text of what has been said. No decisions will be taken based on what the user said, this information will just be passed to a 3<sup>rd</sup> application.</p><p class="yiv347085808MsoNormal"> </p><p class="yiv347085808MsoNormal">I don’t know if this can be achieved or not without developing grammars (not suitable for open-ended dialogs) or training statistical language models. What I do recall is using Dragon Speak in MS word for dictation, without the need of doing some trtraining or developing grammars. That’s exactly what I’m pursuing: a simple plain text transcription of the spoken words.</p><p class="yiv347085808MsoNormal"> </p><p
class="yiv347085808MsoNormal">Have anyone of you deal with something like this by any chance?</p><p class="yiv347085808MsoNormal"> </p><p class="yiv347085808MsoNormal">Thanks for your help. I apologize if this is not the right place to ask this type of questions.</p><p class="yiv347085808MsoNormal"> </p><p class="yiv347085808MsoNormal">Thanks again,</p><p class="yiv347085808MsoNormal">Hector</p></div></div><br>-----Anexo incorporado-----<br><br><div class="plainMail">_______________________________________________<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-users mailing list<br><a ymailto="mailto:FreeSWITCH-users@lists.freeswitch.org" href="/mc/compose?to=FreeSWITCH-users@lists.freeswitch.org">FreeSWITCH-users@lists.freeswitch.org</a><br><a href="http://lists.freeswitch.org/mailman/listinfo/freeswitch-users"
target="_blank">http://lists.freeswitch.org/mailman/listinfo/freeswitch-users</a><br>UNSUBSCRIBE:<a href="http://lists.freeswitch.org/mailman/options/freeswitch-users" target="_blank">http://lists.freeswitch.org/mailman/options/freeswitch-users</a><br><a href="http://www.freeswitch.org" target="_blank">http://www.freeswitch.org</a><br></div></blockquote></td></tr></table>