Theefficiency of algorithmsfor probabilistic inference in Bayesian networks can be improvedby exploiting independenceof causal influence. Thefactorized representation of independe...
This paper presents a new approach to speech synthesis in which a set of cross-word decision-tree state-clustered context-dependent hidden Markov models are used to define a set o...
We answer a problem posed in [GKM08] regarding a restricted model of small-space computation, tailored for solving the GEN problem. They define two variants of “incremental bra...
In this paper, we propose a novel dependency-based bracketing transduction grammar for statistical machine translation, which converts a source sentence into a target dependency t...
Jinsong Su, Yang Liu, Haitao Mi, Hongmei Zhao, Yaj...
The use of statically compiled search networks for ASR systems using huge vocabularies and complex language models often becomes challenging in terms of memory requirements. Dynam...