Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1997-11-21
2000-06-06
Hudspeth, David R.
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704256, G10L 1508
Patent
active
060730986
ABSTRACT:
An approximate weighted finite-state automaton can be constructed in place of a weighted finite-state automaton so long as the approximate weighted finite-state automaton maintains a sufficient portion of the original best strings in the weighted finite-state automaton and sufficiently few spurious strings are introduced into the approximate weighted finite-state automaton compared to the weighted finite-state automaton. An approximate weighted finite-state automaton can be created from a non-deterministic weighted finite-state automaton during determinization by discarding the requirement that old states be used in place of new states only when an old state is identical to a new state. Instead, in an approximate weighted finite-state automaton, old states will be used in place of new states when each of the remainders of the new state is sufficiently close to the corresponding remainder of the old state. An error tolerance parameter .tau. defines whether the remainders of the new state are sufficiently close to the corresponding remainders of the old state. If the remainders of the new state are sufficiently close to the remainders of the old state, a new transition is created from a current state to the old state rather than the new state. Such approximate weighted finite-state automata allow the size of the resulting deterministic finite-state automata to be reduced and can prevent the expansion that would otherwise occur in some deterministic finite-state automata.
REFERENCES:
patent: 4718092 (1988-01-01), Klovstad
patent: 5787396 (1998-07-01), Komori et al.
patent: 5794198 (1998-08-01), Takahashi et al.
D. Breslauer, The Suffix Tree of a Tree and Minimizing Sequential Transducers; 7.sup.th Symposium on Computation Pattern Matching, Feb. 12, 1996, pp. 1-16.
A. Buchsbaum et al., On Reduction via Determinization of Speech-Recognition Lattices, AT&T Labs-Research Technical Report, Jul. 8, 1997, pp. 1-31.
F. Jelinek et al., Principles of Lexical Language Modeling for Speech Recognition, Advances in Speech Signal Processing, Marcel Dekker, Inc., 1992; pp. 651-699.
M. Mohri, Minimization of Sequential Transducers, 5.sup.th Annual Symposium on Computational Pattern Matching, (published in Lecture Notes on Computer Science 807), 1994, pp. 151-163.
M. Mohri, Finite-State Transducers in Language and Speech Processing, Computational Linguistics, vol. 23, #2, Jun. 1997, pp. 1-42.
M. Mohri, On some applications of finite-state automata theory to natural language processing, Natural Language Engineering 2(1): 61-80, 1996 Cambridge University Press, pp. 61-80.
F.C.N. Pereira et al., Speech Recognition by Composition of Weighted Finite Automata, Finite State Language Processing, MIT Press, 1997, pp. 1-24.
F. Pereira et al., Weighted Rational Transductions and their Application to Human Language Processing, Proc. ARPA Human Language Tech. Wksp., 1994, pp. 249-254.
M. Rabin, Probabilistic Automata, Information and Control 6, 1963, pp. 230-245.
L.R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, Stochastic Approaches, IEEE, 1989, pp. 267-296.
C. Reutenauer et al., Minimization of Rational Word Functions, SIAM J. Comput. vol. 20, No. 4, Aug. 1991, pp. 669-685.
E. Roche, Smaller Representions for Finite-State Transduceer and Finite-State Automata, 6 Symposium on Comp. Pattern Matching, 1995, (pub. in Lect. Notes on Computer Science 937 (pp. 352-365)).
Buchsbaum Adam Louis
Giancarlo Raffaele
Westbrook Jeffery Rex
AT&T Corporation
Hudspeth David R.
Lerner Martin
LandOfFree
Method and apparatus for generating deterministic approximate we does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for generating deterministic approximate we, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for generating deterministic approximate we will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2222966