In this paper, we present an algorithm for speech input statistical translation. This algorithm is a dynamic-programming based algorithm, which uses a word graph in the input as a representation of the acoustic of a given utterance. A beam-search implementation of this algorithm has been made and experimental results with the so called EUTRANS-I task are presented. © Springer-Verlag Berlin Heidelberg 2004.
CITATION STYLE
García-Varea, I., Sanchis, A., & Casacuberta, F. (2004). A decoding algorithm for speech input statistical translation. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3206, pp. 307–314). Springer Verlag. https://doi.org/10.1007/978-3-540-30120-2_39
Mendeley helps you to discover research relevant for your work.