We introduce a direct model for speech recognition that assumes an unstructured, i.e., flat text output. The flat model allows us to model arbitrary attributes and dependences o...
Georg Heigold, Geoffrey Zweig, Xiao Li, Patrick Ng...
In large vocabulary continuous speech recognition, decision trees are widely used to cluster triphone states. In addition to commonly used phonetically based questions, others hav...
Hank Liao, Christopher Alberti, Michiel Bacchiani,...
Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabula...
In this paper the optimal filter-bank design method based on the Minimum Phone Error (MPE) criteria is investigated. We use Gaussian type filter bank for optimization and variou...
We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four “morphologically rich” languages: Finnish, Estonian, Turkish, and ...