A common problem in speech recognition for foreign accented speech is that there is not enough training data for an accent-specific or a speaker-specific recognizer. Speaker ada...
This paper reports our recent exploration of the layer-by-layer learning strategy for training a multi-layer generative model of patches of speech spectrograms. The top layer of t...
Li Deng, Michael L. Seltzer, Dong Yu, Alex Acero, ...
We introduce a novel mechanism for incorporating articulatory dynamics into speech recognition with the theory of task dynamics. This system reranks sentencelevel hypotheses by th...
This paper describes an approach for computing a consensus translation from the outputs of multiple machine translation (MT) systems. The consensus translation is computed by weigh...
Evgeny Matusov, Gregor Leusch, Rafael E. Banchs, N...
We describe a fast and efficient online algorithm for phoneme sequence speech recognition. Our method is using a discriminative training to update the model parameters one utteran...