Add to ORKGIn many applications of speech and language processing, we generate intermediate results in the form of a lattice on which we apply finite-state operations. For example, we might POS tag the words in an ASR output lattice as an intermediate stage for language modeling. Currently, we have to convert the lattice into n-best scoring sub-lattices (one sub-lattice per unique inpu
International audienceWe define the locally maximal subwords and locally minimal superwords common t...
International audienceWe define the locally maximal subwords and locally min- imal superwords common...
This work describes the characteristics of state grammars and n-limited state grammars with a focus ...
This paper presents the benefit of using multiple lexical units in the post-processing stage of an A...
A lot of work remains to be done in the domain of a better integration of speech recognition and lan...
International audienceThis paper presents the benefit of using multiple lexical units in the post-pr...
The acoustic model in modern speech recognisers is trained discriminatively, for example with the mi...
redpony, smara, resnik AT umd.edu Word lattice decoding has proven useful in spoken language transla...
This paper introduces lattice based language models, a new language modeling paradigm. These models ...
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the...
This thesis develops a robust inventory of large-scale lattice rescoring methods that improve the qu...
Finite-state methods are finding ever increasing use among linguists as a way of modeling phonology ...
Introduction In response to an input sentence, a typical recognition system (be it speech or handwr...
In this paper we describe the statistical machine transla-tion system developed at ITI/UPV, which ai...
This paper explores lexicographic semirings and their application to problems in speech and language...
International audienceWe define the locally maximal subwords and locally minimal superwords common t...
International audienceWe define the locally maximal subwords and locally min- imal superwords common...
This work describes the characteristics of state grammars and n-limited state grammars with a focus ...
This paper presents the benefit of using multiple lexical units in the post-processing stage of an A...
A lot of work remains to be done in the domain of a better integration of speech recognition and lan...
International audienceThis paper presents the benefit of using multiple lexical units in the post-pr...
The acoustic model in modern speech recognisers is trained discriminatively, for example with the mi...
redpony, smara, resnik AT umd.edu Word lattice decoding has proven useful in spoken language transla...
This paper introduces lattice based language models, a new language modeling paradigm. These models ...
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the...
This thesis develops a robust inventory of large-scale lattice rescoring methods that improve the qu...
Finite-state methods are finding ever increasing use among linguists as a way of modeling phonology ...
Introduction In response to an input sentence, a typical recognition system (be it speech or handwr...
In this paper we describe the statistical machine transla-tion system developed at ITI/UPV, which ai...
This paper explores lexicographic semirings and their application to problems in speech and language...
International audienceWe define the locally maximal subwords and locally minimal superwords common t...
International audienceWe define the locally maximal subwords and locally min- imal superwords common...
This work describes the characteristics of state grammars and n-limited state grammars with a focus ...