Speech Recognition by Composition of Weighted Finite Automata

Details Speech Recognition by Composition of Weighted Finite Automata Speech Recognition by Composition of Weighted Finite Automata

1996-03-07

arxiv.org/abs/cmp-lg/9603001v1

Computer Science

Computation and Language

24 pages, uses psfig.sty

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Speech Recognition by Composition of Weighted Finite Automata does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Speech Recognition by Composition of Weighted Finite Automata, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech Recognition by Composition of Weighted Finite Automata will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-330462