In this paper, we propose a robust compensation strategy to deal effectively with extraneous acoustic variations for spontaneous speech recognition. This strategy extends speaker a...
Independent component analysis (ICA) is not only popular for blind source separation but also for unsupervised learning when the observations can be decomposed into some independe...
This paper introduces a new form of observation distributions for hidden Markov models (HMMs), combining subvector quantization and mixtures of discrete distrib utions. Despite w...
Vassilios Digalakis, S. Tsakalidis, Costas Harizak...
In this paper, we describe a new model for word alignment in statistical translation and present experimental results. The idea of the model is to make the alignment probabilities...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...