Results 1  10
of
73
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.
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.
OpenFst: A general and efficient weighted finitestate transducer library. Implementation and Application of Automata
, 2007
"... Abstract. We describe OpenFst, an opensource library for weighted finitestate transducers (WFSTs). OpenFst consists of a C++ template library with efficient WFST representations and over twentyfive operations for constructing, combining, optimizing, and searching them. At the shellcommand level, ..."
Abstract

Cited by 72 (8 self)
 Add to MetaCart
Abstract. We describe OpenFst, an opensource library for weighted finitestate transducers (WFSTs). OpenFst consists of a C++ template library with efficient WFST representations and over twentyfive operations for constructing, combining, optimizing, and searching them. At the shellcommand level, there are corresponding transducer file representations and programs that operate on them. OpenFst is designed to be both very efficient in time and space and to scale to very large problems. This library has key applications speech, image, and natural language processing, pattern and string matching, and machine learning. We give an overview of the library, examples of its use, details of its design that allow customizing the labels, states, and weights and the lazy evaluation of many of its operations. Further information and a download of the OpenFst library can be obtained from
Graphical models and automatic speech recognition
 Mathematical Foundations of Speech and Language Processing
, 2003
"... Graphical models provide a promising paradigm to study both existing and novel techniques for automatic speech recognition. This paper first provides a brief overview of graphical models and their uses as statistical models. It is then shown that the statistical assumptions behind many pattern recog ..."
Abstract

Cited by 67 (13 self)
 Add to MetaCart
Graphical models provide a promising paradigm to study both existing and novel techniques for automatic speech recognition. This paper first provides a brief overview of graphical models and their uses as statistical models. It is then shown that the statistical assumptions behind many pattern recognition techniques commonly used as part of a speech recognition system can be described by a graph – this includes Gaussian distributions, mixture models, decision trees, factor analysis, principle component analysis, linear discriminant analysis, and hidden Markov models. Moreover, this paper shows that many advanced models for speech recognition and language processing can also be simply described by a graph, including many at the acoustic, pronunciation, and languagemodeling levels. A number of speech recognition techniques born directly out of the graphicalmodels paradigm are also surveyed. Additionally, this paper includes a novel graphical analysis regarding why derivative (or delta) features improve hidden Markov modelbased speech recognition by improving structural discriminability. It also includes an example where a graph can be used to represent language model smoothing constraints. As will be seen, the space of models describable by a graph is quite large. A thorough exploration of this space should yield techniques that ultimately will supersede the hidden Markov model.
A conditional random field for discriminativelytrained finitestate string edit distance
 In Conference on Uncertainty in AI (UAI
, 2005
"... The need to measure sequence similarity arises in information extraction, object identity, data mining, biological sequence analysis, and other domains. This paper presents discriminative stringedit CRFs, a finitestate conditional random field model for edit sequences between strings. Conditional r ..."
Abstract

Cited by 51 (7 self)
 Add to MetaCart
The need to measure sequence similarity arises in information extraction, object identity, data mining, biological sequence analysis, and other domains. This paper presents discriminative stringedit CRFs, a finitestate conditional random field model for edit sequences between strings. Conditional random fields have advantages over generative approaches to this problem, such as pair HMMs or the work of Ristad and Yianilos, because as conditionallytrained methods, they enable the use of complex, arbitrary actions and features of the input strings. As in generative models, the training data does not have to specify the edit sequences between the given string pairs. Unlike generative models, however, our model is trained on both positive and negative instances of string pairs. We present positive experimental results on several data sets. 1
Weighted automata and weighted logics
 In Automata, Languages and Programming – 32nd International Colloquium, ICALP 2005
, 2005
"... Abstract. Weighted automata are used to describe quantitative properties in various areas such as probabilistic systems, image compression, speechtotext processing. The behaviour of such an automaton is a mapping, called a formal power series, assigning to each word a weight in some semiring. We g ..."
Abstract

Cited by 39 (7 self)
 Add to MetaCart
Abstract. Weighted automata are used to describe quantitative properties in various areas such as probabilistic systems, image compression, speechtotext processing. The behaviour of such an automaton is a mapping, called a formal power series, assigning to each word a weight in some semiring. We generalize Büchi’s and Elgot’s fundamental theorems to this quantitative setting. We introduce a weighted version of MSO logic and prove that, for commutative semirings, the behaviours of weighted automata are precisely the formal power series definable with our weighted logic. We also consider weighted firstorder logic and show that aperiodic series coincide with the firstorder definable ones, if the semiring is locally finite, commutative and has some aperiodicity property. 1
Rational kernels: Theory and algorithms
 Journal of Machine Learning Research
, 2004
"... Many classification algorithms were originally designed for fixedsize vectors. Recent applications in text and speech processing and computational biology require however the analysis of variablelength sequences and more generally weighted automata. An approach widely used in statistical learning ..."
Abstract

Cited by 38 (7 self)
 Add to MetaCart
Many classification algorithms were originally designed for fixedsize vectors. Recent applications in text and speech processing and computational biology require however the analysis of variablelength sequences and more generally weighted automata. An approach widely used in statistical learning techniques such as Support Vector Machines (SVMs) is that of kernel methods, due to their computational efficiency in highdimensional feature spaces. We introduce a general family of kernels based on weighted transducers or rational relations, rational kernels, that extend kernel methods to the analysis of variablelength sequences or more generally weighted automata. We show that rational kernels can be computed efficiently using a general algorithm of composition of weighted transducers and a general singlesource shortestdistance algorithm. Not all rational kernels are positive definite and symmetric (PDS), or equivalently verify the Mercer condition, a condition that guarantees the convergence of training for discriminant classification algorithms such as SVMs. We present several theoretical results related to PDS rational kernels. We show that under some general conditions these kernels are
Segmental minimum Bayesrisk decoding for automatic speech recognition
 IEEE Transactions on Speech and Audio Processing
, 2003
"... Abstract—Minimum BayesRisk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum aposteriori probability (MAP) decoders through Nbest list rescoring and search over word lattices. We present a Segmental Minimum BayesRisk decoding (SMBR) framework that simpl ..."
Abstract

Cited by 31 (9 self)
 Add to MetaCart
Abstract—Minimum BayesRisk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum aposteriori probability (MAP) decoders through Nbest list rescoring and search over word lattices. We present a Segmental Minimum BayesRisk decoding (SMBR) framework that simplifies the implementation of MBR recognizers through the segmentation of the Nbest lists or lattices over which the recognition is to be performed. This paper presents lattice cutting procedures that underly SMBR decoding. Two of these procedures are based on a risk minimization criterion while a third one is guided by wordlevel confidence scores. In conjunction with SMBR decoding, these lattice segmentation procedures give consistent improvements in recognition word error rate (WER) on the Switchboard corpus. We also discuss an application of riskbased lattice cutting to multiplesystem SMBR decoding and show that it is related to other system combination techniques such as ROVER. This strategy combines lattices produced from multiple ASR systems and is found to give WER improvements in a Switchboard evaluation system. Index Terms—ASR system combination, extendedROVER, lattice cutting, minimum Bayesrisk decoding, segmental minimum
Interprocedural analysis of concurrent programs under a context bound
 In TACAS
, 2007
"... Abstract. Analysis of recursive programs in the presence of concurrency and shared memory is undecidable. In previous work, Qadeer and Rehof [23] showed that contextbounded analysis is decidable for recursive programs under a finitestate abstraction of program data. In this paper, we show that con ..."
Abstract

Cited by 29 (7 self)
 Add to MetaCart
Abstract. Analysis of recursive programs in the presence of concurrency and shared memory is undecidable. In previous work, Qadeer and Rehof [23] showed that contextbounded analysis is decidable for recursive programs under a finitestate abstraction of program data. In this paper, we show that contextbounded analysis is decidable for certain families of infinitestate abstractions, and also provide a new symbolic algorithm for the finitestate case. 1
Capturing Practical Natural Language Transformations
"... We study automata for capturing transformations employed by practical natural language processing systems, such as those that translate between human languages. For several variations of finitestate string and tree transducers, we ask formal questions about expressiveness, modularity, teachability, ..."
Abstract

Cited by 27 (0 self)
 Add to MetaCart
We study automata for capturing transformations employed by practical natural language processing systems, such as those that translate between human languages. For several variations of finitestate string and tree transducers, we ask formal questions about expressiveness, modularity, teachability, and generalization.