Speech enhancement systems aim to improve the quality and intelligibility of noisy speech. In this study, we compare two speech enhancement systems based on deep neural networks. The speech intelligibility and quality of both systems was evaluated subjectively, by a Speech Recognition Test based on ...

Recent literature indicates increasing interest in deep neural networks for use in speech enhancement systems. Currently, these systems are mostly evaluated through objective measures of speech quality and/or intelligibility. Subjective intelligibility evaluations of these systems have so far not be...

The relationship between the prevalence of noise induced annoyance and the noise exposure is traditionally described by a cumulative noise metric such as DNL. Such dose-response functions have no restrictions regarding how the dose has been derived, e.g. either a large number of low level noise even...

Although aircraft noise-induced annoyance prevalence rates vary greatly for similar noise exposure levels in different times and places, some suggest that communities have recently reacted more strongly to aircraft noise than in the past. Others regard claims of greater annoyance over time at simila...

A noise survey has been conducted at five Norwegian airports. The two standard questions recommended by ICBEN were included in the questionnaire, and both the verbal and the numerical ICBEN response scales were used. The results were analyzed according to the CTL-method, which provides at convenient...

Det er utført beregninger av støy for helikopteraktiviteten ved St. Olavs hospital i Trondheim for dagens situasjon, for året da nytt redningshelikopter forventes å ha overtatt og for en prognose ti år fram i tid. Dagens situasjon er basert på trafikktallene for 2014 og...