We present core aspects of a fully implemented generation component in a multilingual speechto-speech dialogue translation system. Its design was particularly influenced by the ne...
Tilman Becker, Wolfgang Finkler, Anne Kilger, Pete...
Monaural speech segregation in reverberant environments is a very difficult problem. We develop a supervised learning approach by proposing an objective function that directly rel...
This paper presents a hybrid technique combining the Karhonen-Loeve Transform (KLT), the Multilayer Perceptron (MLP) and Genetic Algorithms (GAs) to obtain less-variant Mel-freque...
Sid-Ahmed Selouani, Habib Hamam, Douglas D. O'Shau...
Increasing amounts of public, corporate, and private speech data are now available on-line. These are limited in their usefulness, however, by the lack of tools to permit their br...
Steve Whittaker, Julia Hirschberg, Brian Amento, L...
Various calculation of matrices and vectors has been used in many digital signal processing systems. Although the calculation simply repeats multiplication and addition, the reite...