Graham Coleman

Learn More
We present a novel representation and method for detecting and explaining anomalous activities in a video stream. Drawing from natural language processing, we introduce a representation of activities as bags of event n-grams, where we analyze the global structural information of activities using their local event statistics. We demonstrate how maximal(More)
Several binaural audio signal enhancement algorithms were evaluated with respect to their potential to improve speech intelligibility in noise for users of bilateral cochlear implants (CIs). 50% speech reception thresholds (SRT50) were assessed using an adaptive procedure in three distinct, realistic noise scenarios. All scenarios were highly nonstationary,(More)
This work outlines the concept of personal sample library, a large database of event-synchronous audio segments extracted from a user’s digital music collection. It identifies tasks involved in making sample-based music and audio collage, and shows how interfaces to the personal sample library can aid these tasks and simplify the music development cycle. In(More)
In a collaborative research project, several monaural and binaural noise reduction algorithms have been comprehensively evaluated. In this article, eight selected noise reduction algorithms were assessed using instrumental measures, with a focus on the instrumental evaluation of speech intelligibility. Four distinct, reverberant scenarios were created to(More)
We propose a strategy for integrating descriptor-driven transformation into mosaicing sound synthesis, in which samples are selected by taking into account potential distances in the transformed space. Target descriptors consisting of chroma, mel-spaced filter banks, and energy are modeled with respect to windowed bandlimited resampling and mel-spaced(More)
We propose and present an example system design for predicting <i>changes</i> in perceptually relevant audio properties under the effects of common musical and sonic transformations. By building these predictive models, we may facilitate descriptor-driven control of effects while avoiding queries to the transformation itself. In this study we model spectral(More)
This thesis addresses the problem of creating music collectively on the basis of a shared repository of sound files. The classification of sounds in an heterogeneous database according to both a semantic taxonomy and a music oriented taxonomy based on content descriptors are analyzed, and their application to music creation is discussed. A data structure is(More)
Estimating non-linearities in phase differences between channel pairs of a multi-channel audio recording in a reverberant environment provides more precise spatial information that yields direct improvement in signal enhancement, as we show for the case of source separation. In this study, we propose an online method for estimating inter-channel phase(More)