We present supervised approaches for detecting speaker roles and agreement/disagreement between speakers in broadcast conversation shows in three languages: English, Arabic, and M...
The performance of a fixed beamformer highly depends on the position of the microphones in the array. In this paper, different heuristic optimisation approaches for arbitrary pla...
We describe a new approach for phoneme recognition which aims at minimizing the phoneme error rate. Building on structured prediction techniques, we formulate the phoneme recogniz...
Integer lapped orthogonal transforms (LOTs) are vital technologies for the unification of lossless and lossy image coding, called losslessto-lossy image coding. In this paper, we...
Counts from large corpora (like the web) can be powerful syntactic cues. Past work has used web counts to help resolve isolated ambiguities, such as binary noun-verb PP attachment...