Results 1  10
of
21
Weighted finitestate transducers in speech recognition
 COMPUTER SPEECH & LANGUAGE
, 2002
"... We survey the use of weighted finitestate transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for hidden Markov models (HMMs), contextdependency, pronunciation dictionaries, grammars, and alternative recognition outputs. Furthermore, general tr ..."
Abstract

Cited by 143 (4 self)
 Add to MetaCart
We survey the use of weighted finitestate transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for hidden Markov models (HMMs), contextdependency, pronunciation dictionaries, grammars, and alternative recognition outputs. Furthermore, general transducer operations combine these representations flexibly and efficiently. Weighted determinization and minimization algorithms optimize their time and space requirements, and a weight pushing algorithm distributes the weights along the paths of a weighted transducer optimally for speech recognition. As an example, we describe a North American Business News (NAB) recognition system built using these techniques that combines the HMMs, full crossword triphones, a lexicon of 40 000 words, and a large trigram grammar into a single weighted transducer that is only somewhat larger than the trigram word grammar and that runs NAB in realtime on a very simple decoder. In another example, we show that the same techniques can be used to optimize lattices for secondpass recognition. In a third example, we show how general automata operations can be used to assemble lattices from different recognizers to improve recognition performance.
The Design Principles of a Weighted FiniteState Transducer Library
 THEORETICAL COMPUTER SCIENCE
, 2000
"... We describe the algorithmic and software design principles of an objectoriented library for weighted finitestate transducers. By taking advantage of the theory of rational power series, we were able to achieve high degrees of generality, modularity and irredundancy, while attaining competitive eff ..."
Abstract

Cited by 99 (23 self)
 Add to MetaCart
We describe the algorithmic and software design principles of an objectoriented library for weighted finitestate transducers. By taking advantage of the theory of rational power series, we were able to achieve high degrees of generality, modularity and irredundancy, while attaining competitive efficiency in demanding speech processing applications involving weighted automata of more than 10^7 states and transitions. Besides its mathematical foundation, the design also draws from important ideas in algorithm design and programming languages: dynamic programming and shortestpaths algorithms over general semirings, objectoriented programming, lazy evaluation and memoization.
SEMIRING FRAMEWORKS AND ALGORITHMS FOR SHORTESTDISTANCE PROBLEMS
, 2002
"... We define general algebraic frameworks for shortestdistance problems based on the structure of semirings. We give a generic algorithm for finding singlesource shortest distances in a weighted directed graph when the weights satisfy the conditions of our general semiring framework. The same algorit ..."
Abstract

Cited by 72 (20 self)
 Add to MetaCart
We define general algebraic frameworks for shortestdistance problems based on the structure of semirings. We give a generic algorithm for finding singlesource shortest distances in a weighted directed graph when the weights satisfy the conditions of our general semiring framework. The same algorithm can be used to solve efficiently classical shortest paths problems or to find the kshortest distances in a directed graph. It can be used to solve singlesource shortestdistance problems in weighted directed acyclic graphs over any semiring. We examine several semirings and describe some specific instances of our generic algorithms to illustrate their use and compare them with existing methods and algorithms. The proof of the soundness of all algorithms is given in detail, including their pseudocode and a full analysis of their running time complexity.
Path Kernels and Multiplicative Updates
 Journal of Machine Learning Research
, 2003
"... Kernels are typically applied to linear algorithms whose weight vector is a linear combination of the feature vectors of the examples. Online versions of these algorithms are sometimes called "additive updates" because they add a multiple of the last feature vector to the current weight vector. ..."
Abstract

Cited by 61 (7 self)
 Add to MetaCart
Kernels are typically applied to linear algorithms whose weight vector is a linear combination of the feature vectors of the examples. Online versions of these algorithms are sometimes called "additive updates" because they add a multiple of the last feature vector to the current weight vector.
Generic EpsilonRemoval and Input EpsilonNormalization Algorithms for Weighted Transducers
, 2000
"... We present a new generic removal algorithm for weighted automata and transducers de ned over a semiring. The algorithm can be used with any semiring covered by our framework and works with any queue discipline adopted. It can be used in particular in the case of unweighted automata and transduc ..."
Abstract

Cited by 19 (10 self)
 Add to MetaCart
We present a new generic removal algorithm for weighted automata and transducers de ned over a semiring. The algorithm can be used with any semiring covered by our framework and works with any queue discipline adopted. It can be used in particular in the case of unweighted automata and transducers and weighted automata and transducers de ned over the tropical semiring. It is based on a general shortestdistance algorithm that we briey describe. We give a full description of the algorithm including its pseudocode and its running time complexity, discuss the more ecient case of acyclic automata, an onthey implementation of the algorithm and an approximation algorithm in the case of the semirings not covered by our framework. We illustrate the use of the algorithm with several semirings. We also describe an input normalization algorithm for weighted transducers based on the general shortestdistance algorithm.
The online shortest path problem under partial monitoring
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2007
"... The online shortest path problem is considered under partial monitoring scenarios. At each round, a decision maker has to choose a path between two distinguished vertices of a weighted directed acyclic graph whose edge weights can change in an arbitrary (adversarial) way such that the loss of the ..."
Abstract

Cited by 19 (6 self)
 Add to MetaCart
The online shortest path problem is considered under partial monitoring scenarios. At each round, a decision maker has to choose a path between two distinguished vertices of a weighted directed acyclic graph whose edge weights can change in an arbitrary (adversarial) way such that the loss of the chosen path (defined as the sum of the weights of its composing edges) be small. In the multiarmed bandit setting, after choosing a path, the decision maker learns only the weights of those edges that belong to the chosen path. For this scenario, an algorithm is given whose average cumulative loss in n rounds exceeds that of the best path, matched offline to the entire sequence of the edge weights, by a quantity that is proportional to 1 / √n and depends only polynomially on the number of edges of the graph. The algorithm can be implemented with linear complexity in the number of rounds n and in the number of edges. This result improves earlier banditalgorithms which have performance bounds that either depend exponentially on the number of edges or converge to zero at a slower rate than O(1 / √n). An extension to the socalled label efficient setting is also given, where the decision maker is informed about the weight of the chosen path only with probability ɛ < 1. Applications to routing in packet switched networks along with simulation results are also presented.
An Efficient Algorithm for the nBestStrings Problem
 In Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP ’02
, 2002
"... problem in a weighted automaton. This problem arises commonly in speech recognition applications when a ranked list of unique recognizer hypotheses is desired. We believe this is the first nbest algorithm to remove redundant hypotheses before rather than after the nbest determination. We give a de ..."
Abstract

Cited by 18 (2 self)
 Add to MetaCart
problem in a weighted automaton. This problem arises commonly in speech recognition applications when a ranked list of unique recognizer hypotheses is desired. We believe this is the first nbest algorithm to remove redundant hypotheses before rather than after the nbest determination. We give a detailed description of the algorithm and demonstrate its correctness. We report experimental results showing its efficiency and practicality even for large n in a 40; 000word vocabulary North American Business News (NAB) task. In particular, we show that 1000best generation in this task requires negligible added time over recognizer lattice generation.
A Weight Pushing Algorithm for Large Vocabulary Speech Recognition
 IN EUROPEAN CONF. ON SPEECH COMMUNICATION AND TECHNOLOGY
, 2001
"... Weighted finitestate transducers provide a general framework for the representation of the components of speech recognition systems; language models, pronunciation dictionaries, contextdependent models, HMMlevel acoustic models, and the output word or phone lattices can all be represented by weigh ..."
Abstract

Cited by 16 (10 self)
 Add to MetaCart
Weighted finitestate transducers provide a general framework for the representation of the components of speech recognition systems; language models, pronunciation dictionaries, contextdependent models, HMMlevel acoustic models, and the output word or phone lattices can all be represented by weighted automata and transducers. In general, a representation is not unique and there may be different weighted transducers realizing the same mapping. In particular, even when they have exactly the same topology with the same input and output labels, two equivalent transducers may differ by the way the weights are distributed along each path. We present
Tracking the best quantizer
, 2008
"... An algorithm is presented for online prediction that allows to track the best expert efficiently even when the number of experts is exponentially large, provided that the set of experts has a certain additive structure. As an example, we work out the case where each expert is represented by a path ..."
Abstract

Cited by 12 (6 self)
 Add to MetaCart
An algorithm is presented for online prediction that allows to track the best expert efficiently even when the number of experts is exponentially large, provided that the set of experts has a certain additive structure. As an example, we work out the case where each expert is represented by a path in a directed graph and the loss of each expert is the sum of the weights over the edges in the path. These results are then used to construct universal limiteddelay schemes for lossy coding of individual sequences. In particular, we consider the problem of tracking the best scalar quantizer that is adaptively matched to the source sequence with piecewise different behavior. A randomized algorithm is presented which can perform, on any source sequence, asymptotically as well as the best scalar quantization algorithm that is matched to the sequence and is allowed to change the employed quantizer for a given number of times. The complexity of the algorithm is quadratic in the sequence length, but at the price of some deterioration in performance, the complexity can be made linear. Analogous results are obtained for sequential multiresolution and multiple description scalar quantization of individual sequences.
Provably Secure Competitive Routing against Proactive Byzantine Adversaries via Reinforcement Learning
 In JHU Tech Report Version 1
, 2003
"... An ad hoc wireless network is an autonomous selforganizing system of mobile nodes connected by wireless links where nodes not in direct range communicate via intevraediary nodes. Routing in ad hoc networks is a challenging problem as a result of highly dynamic topology as well as bandwidth and energ ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
An ad hoc wireless network is an autonomous selforganizing system of mobile nodes connected by wireless links where nodes not in direct range communicate via intevraediary nodes. Routing in ad hoc networks is a challenging problem as a result of highly dynamic topology as well as bandwidth and energy constraints. The Swarm Intelligence paradigm has recently been demonstrated as an effective approach for routing in small static network configurations with no adversarial intervention. These algorithms have also been proven to be robust and resilient to changes in node configuration. However, none of the existing routing algorithms can withstand a dynamic proactive adversarial attack, where the network may be completely controlled by byzantine adversaries.