BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Spoken Dialogue Systems for Space and Lunar Exploration - Jim Hier
 onymus (NASA Ames Research Center)
DTSTART:20080527T120000Z
DTEND:20080527T130000Z
UID:TALK12303@talks.cam.ac.uk
CONTACT:Dr Marcus Tomalin
DESCRIPTION:Building spoken dialogue systems for space applications requir
 es systems which are flexible\, portable to new applications\, robust to n
 oise and able to discriminate between speech intended for the system and c
 onversations with other astronauts and systems.  Our systems are built to 
 be flexible by using general typed unification grammars for the language m
 odels which can be specialized using example data.  These are designed so 
 that most sensible ways of expressing a request are correctly recognized s
 emantically.  The language models are tuned with extensive user feedback a
 nd data if available.  The International Space Station and the EVA Suits a
 re noisy (76 and 70 dB SPL).  This noise is best minimized by using active
  noise canceling microphones which permit accurate speech recognition. Fin
 ally open microphone speech recognition is important to hands free\, alway
 s available operation.  Out of domain utterance rejection in its most simp
 le form depends on careful adjustment of rejection thresholds for both aco
 ustic and natural language scores so that out of domain rejection is near 
 97 % and the false rejection rate is around 5 %.  This means that astronau
 ts can talk to each other and by radio to the ground without the system fa
 lsely recognizing a command or query.  The effect of statistical and lingu
 istically motivated language modeling techniques will be discussed and sho
 wn to be of comparable performance.  A short clip of the surface suit spok
 en dialogue system being used in a field test will be shown.
LOCATION:LR5\, Engineering Department\, Baker Building
END:VEVENT
END:VCALENDAR