
Miles ThorogoodUniversity of British Columbia - Okanagan | UBC Okanagan · Department of Creative Studies
Miles Thorogood
Doctor of Philosophy
Building Sonic Production Research Intelligence and Applications Lab infrastructure at UBC.
About
34
Publications
15,384
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
470
Citations
Introduction
Miles Thorogood researches, designs, and develops adaptive and interactive software systems. Current research interests include artificial intelligence and semantic representations of media, in the broader context of understanding creativity.
He is a creative consultant and developer, designing and developing engaging experiences through emerging technologies.
Additional affiliations
January 2011 - January 2018
Education
February 2004 - September 2007
Publications
Publications (34)
Sound design plays a critical role in enhancing the impact of audio content for video games and immersive environments. However, the subjective nature of sound perception and aesthetics makes it challenging to define the key features for advancing the development of techniques and tools for analyzing, searching, and organizing sound design signals....
The integration of a speech technology into a digital edition to support the acquisition of a critically endangered Indigenous language is a complex task. More than simply consisting of technical challenges of working with an under-resourced language, researchers face the potential of re-enacting causes of language endangerment without rigorous adh...
This paper presents Waterways Past, Present and Future, a research project and exhibition in Okanagan Syilx territory, aimed at increasing awareness of the relationship between people and water towards catalyzing sustainable water practices. The exhibition’s multi-channel audio-visual media was designed to immerse, provoke, destabilize, transform a...
The 'Light up Kelowna' urban screen features a variety of digital artists who use technology to push art in different and thought-provoking directions, tell our community's vital stories and allow the public to engage with the artwork in a multi-dimensional and multisensory way. In this paper, we outline the structure for coordinating engaged parti...
Waterways Past, Present and Future is an informative interactive media exhibition aimed at increasing awareness of the fragile relationship between people and water in the Okanagan Valley and catalyzing sustainable water practices among residents. The exhibition draws on the power of multi-channel sound and video media to immerse, provoke, destabil...
Soundscape composition and design is the creative practice of processing and combining sound recordings to evoke auditory associations and memories within a listener. We present a new set of classification and segmentation algorithms as part of Audio Metaphor (AUME), a generative system for creating novel soundscape compositions. Audio Metaphor pro...
We discuss the Water Ways project that uses a research-creation approach to bridge scientific, Indigenous, artistic, and humanistic perspectives within media-rich data-driven visualizations. The Water Ways demonstrates how the research-creation method enables articulation and exploration of the nature of human water relationships in the Okanagan Va...
The Aeon instrument is an expressive visual music instrument used for live media to support interdisciplinary performance practice. The Aeon instrument enables generative animation, editing and compositing, tailored for improvisational expression of projected visual elements and spatialized audio. In this paper, we discuss the design of Aeon in ter...
Generative art provides new opportunities for creating sustainable and resilient communities. We discuss three key elements important for the relationship between generative art and sustainability: Dynamic composition, Interdisciplinary development , and Community. Each of these elements is analyzed in relationship to exemplary artwork. We conclude...
Autonomously generating artificial soundscapes for video games, virtual reality, and sound art presents several non-trivial challenges. We outline a system called Audio Metaphor that is built upon the notion that sound design for soundscape compositions is emotionally informed. We first define the problem space of generating soundscape compositions...
Sound designers routinely mix source soundscape recordings. Previous studies have shown that people agree with each other on the perceived valence and arousal for soundscape recordings. This study investigates whether we can compute the perceived emotion of the mixed-soundscape recordings based on the perceived emotion of source soundscape recordin...
Emotion recognition is an open problem in Affective Computing the field. Music emotion recognition (MER) has challenges including variability of musical content across genres, the cultural background of listeners, reliability of ground truth data, and the modeling human hear- ing in computational domains. In this study, we focus on experimental mus...
Soundscape emotion recognition (SER) aims at the automatic recognition of emotions perceived in soundscape recordings. To benchmark SER, we propose a dataset of audio samples called Emo-Soundscapes and two evaluation protocols for machine learning models. We curated 600 soundscape recordings from Freesound.org and mixed 613 audio clips from a combi...
Soundscape affect recognition is essential for sound designers and soundscape composers. Previous work demonstrated the effectiveness of predicting valence and arousal of soundscapes in responses from one expert user. Based on this, we present a method for the automatic soundscape affect recognition using ground truth data collected from an online...
Classification and segmentation are important but time consuming tasks when using soundscape recordings in sound design and research. Background and foreground are criteria when segmenting sound files according to a signal's perceptual attributes. We establish the background and foreground classification task within a musicological and soundscape c...
Creating, disseminating, and maintaining lecture slides has long been the standard model of providing students with presentation cues and lecture notes. We describe a system called slideDeck.js that augments the standard model and generates online slide decks using a minimal markup language. Different slide types include bullet points, images, and...
We describe our research-creation across multiple generative systems, using the parameters of valence and arousal as unifying parameters. A variety of methods have been explored that translate emotional responses in viewers into objective measures; however, most of these are not useful for artists, especially generative artists. However, valence (p...
Segmentation and classification is an important but time consuming part of the process of using soundscape recordings in sound design and research. Background and foreground are general classes referring to a signal's perceptual attributes, and used as a criteria by sound designers when segmenting sound files. We establish the background / foregrou...
A soundscape is the sound environment perceived by a given listener at a given time and space. An automatic soundscape affect recognition system will be beneficial for composers, sound designers, and audio researchers. Previous work on an automatic soundscape affect recognition system has demonstrated the effectiveness of predicting valence and aro...
We present a new media work, MediaScape, which is an initial foray into a fully interdisciplinary metacreativity. This paper defines metacreation, and we present examples of metacreative art within the fields of music, sound art, the history of generative narrative, and discuss the potential of the “open-documentary” as an immediate goal of metacre...
Metacreation is a contemporary approach to generative art, using tools and techniques from artificial intelli-gence, artificial life, and machine learning (themselves inspired by cognitive and life sciences) to develop soft-ware that is creative on its own. We present examples of metacreative art within the fields of music, sound art, the history o...
Soundscape composition in improvisation and performance contexts involves many processes that can become overwhelming for a performer, impacting on the quality of the composition. One important task is evaluating the mood o fa composition for evoking accurate associations and memories of a soundscape. We present a new system called Impress that use...
We have developed an audio information retrieval system, named Audio Metaphor. It is designed for use in soundscape composition. Audio Metaphor accepts natural language queries, and recommends audio files from online collaborative databases. Audio Metaphor uses a sub-query generation algorithm, named SLiCE (String List Chopping Experiment) that acc...
Chatter and Listening is a project that creates a number of re-locatable art objects with sonic attributes. These objects act as single entities; they can create decisions, observe their environment and operate alone. They also act in the narrative of a colony where each entity is guided in behaviour by the state of the colony and its surrounding e...
Jogging is a healthy activity and many people enjoy jogging with others for social and motivational reasons. However, jogging partners might not always live in the same location, and it may be difficult to find a local jogger who runs at the same pace, we found through a survey "Jogging over a Distance" allows geographically distant joggers to soci...
Sport is a domain full of movement-based interactions. These interactions typically have positive health effects as well as
an impact on social bonding. We have investigated ways in which computer augmented devices can lead to new sport experiences
and explored opportunities to combine physical activities with remote social bonding. Three prototype...
Jogging is a healthy activity and many people enjoy jogging with others for social and motivational reasons. However, jogging partners might not always live in the same location, and it may be difficult to find a local jogger who runs at the same pace, we found through a survey "Jogging over a Distance" allows geographically distant joggers to soci...
This paper describes an algorithmic drum perform-ance device for musical expression. The idea is to provide maximum variation and dynamics with minimal input. An algorithm programmed into a PIC micro-controller acts as the 'brains' of the device taking data from inputs and forming an equation with the variables, outputting the result to an audio dr...
Jogging is a healthy activity and many people enjoy jogging with others for social and motivational reasons. However, jogging partners might not always live in the same location, and it may be difficult to find a local jogger who runs at the same pace, we found through a survey. We present "Jogging over a Distance", which allows joggers to socializ...