Meliani, R. E. and O'Shaughnessy, D. (1996). New efficient fillers for unlimited word recognition and keyword spotting. In Proc. ICSLP'96, Philadelphia, Pennsylvania, USA. Report 231 Home/Search Document Details and Download
Summary Related Articles |
This paper is cited in the following contexts:
Detection and Transcription of OOV Words - Fetter (1998) (3 citations) (Correct)
....words sequences contained among the N 3 This is why LVCSR log likelihood ratio scoring is also called N best likelihood ratio. Report 231 best candidates. Using LVCSR log likelihood ratio scoring, a significantly better performance was obtained than with time normalized Viterbi scores. In [Meliani and O Shaughnessy, 1996] El Meliani et al. propose using common techniques for both OOV word modeling in large vocabulary continuous speech recognition and garbage (or filler) modeling in keyword spotting. They present experimental results on using different kinds of filler models at the lexical level (that is, garbage ....
Meliani, R. E. and O'Shaughnessy, D. (1996). New efficient fillers for unlimited word recognition and keyword spotting. In Proc. ICSLP'96, Philadelphia, Pennsylvania, USA. Report 231
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC