Carnegie Mellon University
file.pdf (249.42 kB)
Download file

Combining Slot-based Vector Space Model for Voice Book Search

Download (249.42 kB)
journal contribution
posted on 2011-08-01, 00:00 authored by Cheongjae Lee, Tatsuya Lee, Alexander RudnickyAlexander Rudnicky

We describe a hybrid approach to vector space model that improves accuracy in voice search for books. We compare different vector space approaches and demonstrate that the hybrid search model using a weighted sub-space model smoothed with a general model and a back-off scheme provides the best search performance on natural queries obtained from the Web.


Publisher Statement

The final publication is available at Springer via



Usage metrics