ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Silence models in weighted finite-state transducers

Philip N. Garner

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.


doi: 10.21437/Interspeech.2008-499

Cite as: Garner, P.N. (2008) Silence models in weighted finite-state transducers. Proc. Interspeech 2008, 1817-1820, doi: 10.21437/Interspeech.2008-499

@inproceedings{garner08_interspeech,
  author={Philip N. Garner},
  title={{Silence models in weighted finite-state transducers}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={1817--1820},
  doi={10.21437/Interspeech.2008-499}
}