Arild Brandrud Næss

Norwegian University of Science and Technology | NTNU · Trondheim Business School

Recognizing aspects of articulation from audio recordings of speech is an important problem, either as an end in itself or as part of an articulatory approach to automatic speech recognition. In this paper we study the frame-level classification of a set of articulatory features (AFs) inspired by the vocal tract variables of articulatory phonology....

In this paper we present two approaches to adapt a syllable-based recognition lexicon in an automatic speech recognition (ASR) setting. The motivation is to evaluate whether adaptation techniques commonly used on a word level can also be employed on a subword level. The first method predicts syllable variations, taking into account sub-syllabic pho...

Formålet med denne studien er å undersøke hvorvidt maskinlæringsteknikker er bedre i stand til å estimere modeller for konkursprediksjon enn tradisjonelle statistiske metoder. Konkursprediksjonsmodeller estimeres ved hjelp av tre maskinlæringsteknikker (nevrale nettverk, støttevektormaskiner og k-nærmeste naboer) og to regresjonsmetoder (logistisk...

Fluctuations in visitor numbers over the past 50 years at the Norwegian University of Science and Technology (NTNU) Museum of Natural History and Archaeology in Trondheim, Norway, indicate an overall decline in visitation since the 1990s but with some positive figures in the last years. Separate data available from 1977 to 2006 show a strong correl...