ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Language modeling for what-with-where on GOOG-411

Charl van Heerden, Johan Schalkwyk, Brian Strope

This paper describes the language modeling architectures and recognition experiments that enabled support of ‘what-with-where’ queries on GOOG-411. First we compare accuracy trade-offs between a single national business LM for business queries and using many small models adapted for particular cities. Experimental evaluations show that both approaches lead to comparable overall accuracy. Differences in the distributions of errors also lead to improvements from a simple combination. We then optimize variants of the national business LM in the context of combined business and location queries from the web, and finally evaluate these models on a recognition test from the recently fielded ‘what-with-where’ system.

doi: 10.21437/Interspeech.2009-294

Cite as: Heerden, C.v., Schalkwyk, J., Strope, B. (2009) Language modeling for what-with-where on GOOG-411. Proc. Interspeech 2009, 991-994, doi: 10.21437/Interspeech.2009-294

  author={Charl van Heerden and Johan Schalkwyk and Brian Strope},
  title={{Language modeling for what-with-where on GOOG-411}},
  booktitle={Proc. Interspeech 2009},