Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
In this paper two methods for the detection and recognition of landmarks to be used in topological modeling for autonomous mobile robots are presented. The first method is based o...
This paper presents a method for automatic multimodal person authentication using speech, face and visual speech modalities. The proposed method uses the motion information to loc...
Named Entity (NE) recognition from the results of Automatic Speech Recognition (ASR) is challenging because of ASR errors. To detect NEs, one of the options is to use a statistica...
Previously we have proposed different models for estimating articulatory gestures and vocal tract variable (TV) trajectories from synthetic speech. We have shown that when deploye...
Vikramjit Mitra, Hosung Nam, Carol Y. Espy-Wilson,...