In this paper we first introduce four kinds of modification of Symmetric Scoring [1] which produce likelihood ratios that do not need to be explicitly normalized, i.e. T-norm, Z...
In this paper, several approaches for language portability of dialogue systems are investigated with a focus on the spoken language understanding (SLU) component. We show that the...
The use of visual information derived from accurate lip extraction, can provide features invariant to noise perturbation for speech recognition systems and can be also used in a w...
Rapidly increasing quantities of multimedia and spoken content today demand fast and accurate retrieval approaches for convenient browsing. The spoken documents with wide variety ...
The performance of a speech recognition system may be degraded even without any background noise because of the linear or non-linear distortions incurred by recording devices or r...