9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Silence Models in Weighted Finite-State Transducers

Philip N. Garner

IDIAP Research Institute, Switzerland

We investigate the effects of different silence modelling strategies in Weighted Finite-State Transducers for Automatic Speech Recognition. We show that the choice of silence models, and the way they are included in the transducer, can have a significant effect on the size of the resulting transducer; we present a means to prevent particularly large silence overheads. Our conclusions include that context-free silence modelling fits well with transducer based grammars, whereas modelling silence as a monophone and a context has larger overheads.

Full Paper

Bibliographic reference.  Garner, Philip N. (2008): "Silence models in weighted finite-state transducers", In INTERSPEECH-2008, 1817-1820.