9 A two-level mixture linear dynamic system model, with frame-level switching parameters in the obser10 vation equation and with segment-level switching parameters in the target-d...
In thispaper, we present a novelhybridarchitecture forcontinuousspeech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is ...
Speech recognition is usually based on Hidden Markov Models (HMMs), which represent the temporal dynamics of speech very efficiently, and Gaussian mixture models, which do non-opt...
We report work on the first component of a two stage speech recognition architecture based on phonological features rather than phones. The paper reports experiments on three phon...