Sciweavers

77 search results - page 4 / 16
» Extended Viterbi algorithm for optimized word HMMS
Sort
View
CSL
2002
Springer
13 years 7 months ago
Weighted finite-state transducers in speech recognition
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for HMM models, context-depend...
Mehryar Mohri, Fernando Pereira, Michael Riley
DSL
2009
13 years 5 months ago
Operator Language: A Program Generation Framework for Fast Kernels
Abstract. We present the Operator Language (OL), a framework to automatically generate fast numerical kernels. OL provides the structure to extend the program generation system Spi...
Franz Franchetti, Frédéric de Mesmay...
ICALP
2005
Springer
14 years 26 days ago
Randomized Fast Design of Short DNA Words
We consider the problem of efficiently designing sets (codes) of equal-length DNA strings (words) that satisfy certain combinatorial constraints. This problem has numerous motivati...
Ming-Yang Kao, Manan Sanghi, Robert T. Schweller
ICCCI
2009
Springer
13 years 5 months ago
Firefly Algorithm for Continuous Constrained Optimization Tasks
Abstract. The paper provides an insight into the improved novel metaheuristics of the Firefly Algorithm for constrained continuous optimization tasks. The presented technique is in...
Szymon Lukasik, Slawomir Zak
PRL
2007
131views more  PRL 2007»
13 years 6 months ago
A new look at discriminative training for hidden Markov models
ct 7 Discriminative training for hidden Markov models (HMMs) has been a central theme in speech recognition research for many years. 8 One most popular technique is minimum classiï...
Xiaodong He, Li Deng