Abstract. In this paper we describe the 2005 AMI system for the transcription of speech in meetings used in the 2005 NIST RT evaluations. The system was designed for participation ...
Thomas Hain, Lukas Burget, John Dines, Giulia Gara...
Abstract. In this paper, we present initial results towards boosting posterior based speech recognition systems by estimating more informative posteriors using multiple streams of ...
This paper describes the audio human computer interface experiments of ixi in the past and outlines the current platform for future research. ixi software [5] was founded by Thor ...
Abstract. Automated Text Categorization has reached the levels of accuracy of human experts. Provided that enough training data is available, it is possible to learn accurate autom...
Abstract. Discriminative and generative methods provide two distinct approaches to machine learning classification. One advantage of generative approaches is that they naturally mo...