Results 1 
8 of
8
FiniteState Transducers
 in Speech Recognition. Computer Speech and Language
, 1997
"... Abstract. psubsequential transducers are efficient finitestate transducers with p final outputs used in a variety of applications. Not all transducers admit equivalent psubsequential transducers however. We briefly describe an existing generalized determinization algorithm for psubsequential tran ..."
Abstract

Cited by 68 (18 self)
 Add to MetaCart
Abstract. psubsequential transducers are efficient finitestate transducers with p final outputs used in a variety of applications. Not all transducers admit equivalent psubsequential transducers however. We briefly describe an existing generalized determinization algorithm for psubsequential transducers and give the first characterization of psubsequentiable transducers, transducers that admit equivalent psubsequential transducers. Our characterization shows the existence of an efficient algorithm for testing psubsequentiability. We have fully implemented the generalized determinization algorithm and the algorithm for testing psubsequentiability. We report experimental results showing that these algorithms are practical in largevocabulary speech recognition applications. The theoretical formulation of our results is the equivalence of the following three properties for finitestate transducers: determinizability in the sense of the generalized algorithm, psubsequentiability, and the twins property. 1
Minimization Algorithms for Sequential Transducers
, 2000
"... We present general algorithms for minimizing sequential finitestate transducers that output strings or numbers. The algorithms are shown to be efficient since in the case of acyclic transducers and for output strings they operate in O(S+E+V+(EV+F)x(Pmax+1)) steps, where S is the sum of ..."
Abstract

Cited by 54 (12 self)
 Add to MetaCart
We present general algorithms for minimizing sequential finitestate transducers that output strings or numbers. The algorithms are shown to be efficient since in the case of acyclic transducers and for output strings they operate in O(S+E+V+(EV+F)x(Pmax+1)) steps, where S is the sum of the lengths of all output labels of the resulting transducer, E the set of transitions of the given transducer, V the set of its states, F the set of final states, and Pmax one of the longest of the longest common prefixes of the output paths leaving each state of the transducer. The algorithms apply to a larger class of transducers which includes subsequential transducers.
Determinization of Finite State Weighted Tree Automata
 J. Autom. Lang. Combin
, 2002
"... We investigate the determinization of nondeterministic bottomup/topdown finite state weighted tree automata over some semiring A and compare the resulting four classes of formal tree series with each other. In fact, we generalize well known theorems on classes of tree languages (cf. [GS84] Chapter ..."
Abstract

Cited by 16 (2 self)
 Add to MetaCart
We investigate the determinization of nondeterministic bottomup/topdown finite state weighted tree automata over some semiring A and compare the resulting four classes of formal tree series with each other. In fact, we generalize well known theorems on classes of tree languages (cf. [GS84] Chapter II, Theorems 2.6 and 2.10, Example 2.11), viz. if A is a commutative and locally finite semifield, then (i) nondeterministic bottomup, (ii) deterministic bottomup, and (iii) nondeterministic topdown finite state weighted tree automata are equally powerful. Moreover, if the input alphabet is not trivial, then deterministic topdown finite state weighted tree automata are strictly less powerful than the aforementioned classes.
Determinization of Transducers Over Infinite Words
"... We study the determinization of transducers over infinite words. We consider transducers with all their states final. We give an effective characterization of sequential functions over infinite words. We also describe an algorithm to determinize transducers over infinite words. ..."
Abstract

Cited by 7 (2 self)
 Add to MetaCart
We study the determinization of transducers over infinite words. We consider transducers with all their states final. We give an effective characterization of sequential functions over infinite words. We also describe an algorithm to determinize transducers over infinite words.
Finitely Subsequential Transducers
, 2003
"... Finitely subsequential transducers are efficient finitestate transducers with a finite number of final outputs and are used in a variety of applications. Not all transducers admit equivalent finitely subsequential transducers however. We briefly describe an existing generalized determinization al ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
Finitely subsequential transducers are efficient finitestate transducers with a finite number of final outputs and are used in a variety of applications. Not all transducers admit equivalent finitely subsequential transducers however. We briefly describe an existing generalized determinization algorithm for finitely subsequential transducers and give the first characterization of finitely subsequentiable transducers, transducers that admit equivalent finitely subsequential transducers. Our characterization shows the existence of an efficient algorithm for testing finite subsequentiability. We have fully implemented the generalized determinization algorithm and the algorithm for testing finite subsequentiability. We report
On the Determinizability of Weighted Automata and Transducers
 In Proceedings of the workshop Weighted Automata: Theory and Applications (WATA
, 2002
"... Finite automata are classical computational devices used in a variety of largescale applications [1]. Finitestate transducers are automata whose transitions are labeled with both an input and an output label. Some applications in text, speech and image processing require more general devices, weig ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
Finite automata are classical computational devices used in a variety of largescale applications [1]. Finitestate transducers are automata whose transitions are labeled with both an input and an output label. Some applications in text, speech and image processing require more general devices, weighted automata, to account for the variability of the input data and to rank various output hypotheses [7, 9, 8]. A weighted automaton is a finite automaton in which each transition is labeled with some weight in addition to the usual symbol. Weighted automata and transducers provide a common representation for each component of a complex system used in these applications and admit general algorithms such as composition which can be used to combine these components. The time efficiency of these systems is substantially increased when deterministic or subsequential machines are used [9] and the size of these machines can be further reduced using general minimization algorithms [9, 10]. A weighted automaton or transducer is deterministic or subsequential if it has a unique initial state and if no two transitions leaving the same state share the same input label. A general determinization algorithm for weighted automata and transducers was given by [9]. The algorithm outputs a deterministic machine equivalent to the input weighted automaton or transducer and is an extension of the classical subset construction used for unweighted finite automata. But, unlike the case of unweighted automata, not all finitestate transducers or weighted automata and transducers can be determinized using this algorithm. In fact, some machines do not admit any equivalent deterministic one. Thus, it is important to design an algorithm for testing the determinizability of finitestate transducers and weighted automata.
An Efficient PreDeterminization Algorithm
 CIAA 2003. LNCS
, 2003
"... We present a general algorithm, predeterminization, that makes an arbitrary weighted transducer over the tropical semiring or an arbitrary unambiguous weighted transducer over a cancellative commutative semiring determinizable by inserting in it transitions labeled with special symbols. After deter ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We present a general algorithm, predeterminization, that makes an arbitrary weighted transducer over the tropical semiring or an arbitrary unambiguous weighted transducer over a cancellative commutative semiring determinizable by inserting in it transitions labeled with special symbols. After determinization, the special symbols can be removed or replaced with εtransitions. The resulting transducer can be significantly more efficient to use. We report empirical results showing that our algorithm leads to a substantial speedup in largevocabulary speech recognition. Our predeterminization algorithm makes use of an efficient algorithm for testing a general twins property, a sufficient condition for the determinizability of all weighted transducers over the tropical semiring and unambiguous weighted transducers over cancellative commutative semirings. It inserts new transitions just when needed to guarantee that the resulting transducer has the twins property and thus is determinizable. It also uses a singlesource shortestpaths algorithm over the minmax semiring for carefully selecting the positions for insertion of new transitions to benefit from the subsequent application of determinization. These positions are proved to be optimal in a sense that we describe.
An Optimal PreDeterminization Algorithm for Weighted Transducers
, 2004
"... We present a general algorithm, predeterminization, that makes an arbitrary weighted transducer over the tropical semiring or an arbitrary unambiguous weighted transducer over a cancellative commutative semiring determinizable by inserting in it transitions labeled with special symbols. After deter ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We present a general algorithm, predeterminization, that makes an arbitrary weighted transducer over the tropical semiring or an arbitrary unambiguous weighted transducer over a cancellative commutative semiring determinizable by inserting in it transitions labeled with special symbols. After determinization, the special symbols can be removed or replaced with #transitions. The resulting transducer can be significantly more e#cient to use. We report empirical results showing that our algorithm leads to a substantial speedup in largevocabulary speech recognition. Our predeterminization algorithm makes use of an e#cient algorithm for testing a general twins property, a su#cient condition for the determinizability of all weighted transducers over the tropical semiring and unambiguous weighted transducers over cancellative commutative semirings. Based on the transitions marked by this test of the twins property, our predeterminization algorithm inserts new transitions just when needed to guarantee that the resulting transducer has the twins property and thus is determinizable. It also uses a singlesource shortestpaths algorithm over the minmax semiring for carefully selecting the positions for insertion of new transitions to benefit from the subsequent application of determinization. These positions are proved to be optimal in a sense that we describe.