BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Syllable based keyword search: transducing syllable lattices to wo
 rd lattices - Jim Hieronymus\, ICSI (US)
DTSTART:20141121T133000Z
DTEND:20141121T143000Z
UID:TALK55918@talks.cam.ac.uk
CONTACT:Rogier van Dalen
DESCRIPTION:This paper presents a weighted finite state transducer (WFST) 
 based syllable decoding and transduction framework for keyword search (KWS
 ). Acoustic context dependent phone models are trained from word forced al
 ignments. Then syllable decoding is done with lattices generated using a s
 yllable lexicon and language model (LM). To process out of vocabulary (OOV
 ) keywords\, pronunciations are produced using a grapheme-to-syllable (G2S
 ) system. Syllables not seen in the training set are approximated by using
  the closest perceptual syllable in the recognized syllable set.  A syllab
 le to word lexical transducer containing both in-vocabulary (IV) and OOV k
 eywords is then constructed and composed with a keyword-boosted LM transdu
 cer. The composed transducer is then used to transduce syllable lattices t
 o word lattices for final KWS. An ngram word sequence LM with the keywords
  boosted\, provides the best performance.  We show that our method can eff
 ectively perform KWS on both IV and OOV keywords\, and yields up to 0.03 A
 ctual Term-Weighted Value (ATWV) improvement over searching keywords direc
 tly in syllable lattices.  Word Error Rates (WER) and KWS results are repo
 rted for five different languages\, comparing whole word\, phonetic confus
 ion and syllable techniques.  Combining the techniques provides even more 
 improvement. \n\n\n*Speaker*\n\nJim Hieronymus is a senior scientist and p
 rincipal investigator at the International Institute for Computer Science 
 in Berkeley\, CA\, USA.  He is a collaborator with the Cambridge Speech Re
 cognition Group in the Engineering Department. He has worked on putting a 
 spoken dialog system on the International Space Station for NASA\, on the 
 EU Trindi project on integrating prosodics into a dialogue system\, and at
  Bell Labs on spoken dialogue systems\, speech recognition and spoken lang
 uage identification.  Before that Jim was a professor at the Center for Sp
 eech Technology Research and the Linguistics Department at Edinburgh Unive
 rsity.\n\nSandwiches will be provided at 13:00\, 30 minutes before the tal
 k.
LOCATION:Department of Engineering - LT2
END:VEVENT
END:VCALENDAR