Speech Recognition by Composition of Weighted Finite Automata
Fernando C. N. Pereira, Michael Riley · The MIT Press eBooks · 1997
We present a general framework based on weighted finite automata and weighted finite-state transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data structures used in recognition, including context-dependent units, pronunciation dictionaries, language models and lattices. Furthermore, general but efficient algorithms can used for combining information sources in actual recognizers and for optimizing their application. In particular, a single composition algorithm is used both to combine in advance information sources such as language models and dictionaries, and to combine acoustic observations and information sources dynamically during recognition. 1 Introduction Many problems in speech processing can be usefully analyzed in terms of the "noisy channel" metaphor: given an observation sequence o, find which intended message w is most likely to generate that observation sequence by maximizing P (w; ...