Hi,<br>I have a asr dialogue with two consecutive play_and_detect_speech calls.<br><br>The say: part is empty and the detect: part uses nuance grxml grammar.<br><br>In the second play_and_detect invocation freeswitch looses some of the userplane data,<br>
thus causing the speech detection to fail.<br><br>From the userplane data forwarded by freeswitch to the Nuance NSS server,<br>about one second of speech is missing in the beginning of the phrase<br><br>If I add say: with some content, then all works fine.<br>
<br>What could cause this loss of userplane data ?<br><br>Cheers /Mike<br><br><br>