Parallel scalability allows an application to efficiently utilize an increasing number of processing elements. In this paper we explore a design space for parallel scalability for...
We propose a new optimization algorithm called Generalized Baum Welch (GBW) algorithm for discriminative training on hidden Markov model (HMM). GBW is based on Lagrange relaxation...
The goal of this study is to evaluate the potential for using large vocabulary continuous speech recognition as an engine for automatically classifying utterances according to the...
Steve Lowe, Anne Demedts, Larry Gillick, Mark Mand...
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
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...