In context-dependent acoustic modeling, it is important to strike a balance between detailed modeling and data sufficiency for robust estimation of model parameters. In the past,...
Long-span language models that capture syntax and semantics are seldom used in the first pass of large vocabulary continuous speech recognition systems due to the prohibitive sea...
Anoop Deoras, Tomas Mikolov, Stefan Kombrink, Mart...
Dynamic process management is a much-needed feature for applications and tools development in Beowulf cluster environment. A welldefined and efficient dynamic process management in...
We describe feature space and model space discriminative training for a new class of acoustic models called Bayesian sensing hidden Markov models (BS-HMMs). In BS-HMMs, speech dat...
This paper introduces a new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM. This model is able to h...
Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-...