This paper considers dynamic language model adaptation for Mandarin broadcast news recognition. Both contemporary newswire texts and in-domain automatic transcripts were exploited...
This paper introduces MOCAS (Model Of Components for Adaptive Systems), a generic state-based component model which enables the self-adaptation of software components together wit...
2 Related Works Gaussian mixtures are often used for data modeling in many real-time applications such as video background modeling and speaker direction tracking. The real-time a...
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...
Abstract. In this paper, we investigate the application of adaptive ensemble models of Extreme Learning Machines (ELMs) to the problem of one-step ahead prediction in (non)stationa...
Mark van Heeswijk, Yoan Miche, Tiina Lindh-Knuutil...