• Publications
  • Influence
Emo-soundscapes: A dataset for soundscape emotion recognition
TLDR
A dataset of audio samples called Emo-Soundscapes and two evaluation protocols for machine learning models to benchmark SER are proposed and how the mixing of various soundscape recordings influences their perceived emotion is studied.
Computationally Created Soundscapes with Audio Metaphor
TLDR
This work presents Audio Metaphor, a system for creating novel soundscape compositions that processes natural language queries derived from Twitter for retrieving semantically linked sound recordings from online user-contributed audio databases.
slideDeck.js: A Platform for Generating Accessible and Interactive Web-Based Course Content
TLDR
A system called slideDeck.js is described that augments the standard model and generates online slide decks using a minimal markup language and is designed to be flexible for instructors to update content, modify the look and feel of the presentation, and transferred between colleagues teaching the course.
Audio Metaphor: Audio Information Retrieval for Soundscape Composition
TLDR
Audio Metaphor facilitated audience interaction by listening for Tweets that the audience addressed to the performance; in this case, it processed the Twitter feed in realtime to recommend audio files to the soundscape composer.
MediaScape: Towards a Video, Music, and Sound Metacreation
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
Ranking-Based Emotion Recognition for Experimental Music
TLDR
This study presents a crowdsourcing method that is used to collect ground truth via ranking the valence and arousal of music clips, and proposes a smoothed RankSVM (SRSVM) method that outperforms four other ranking algorithms.
Automatic Recognition of Eventfulness and Pleasantness of Soundscape
TLDR
A gold standard for soundscape affect recognition is generated by averaging responses from people provided people agreed with each other enough and the correlation between the level of pleasantness and thelevel of eventfulness is tested based upon the gold standard.
Automatic Soundscape Affect Recognition Using A Dimensional Approach
TLDR
A method for the automatic soundscape affect recognition using ground truth data collected from an online survey and a gold standard is presented, which shows that participants have a high level of agreement on the valence and arousal of soundscapes.
Impress: A Machine Learning Approach to Soundscape Affect Classification for a Music Performance Environment
TLDR
A new system called Impress is presented that uses supervised machine learning for the acquisition and realtime feedback of soundscape a↵ect, and an audio features vector of audio descriptors was used to represent an audio signal for fitting multiple regression models to predictsoundscape a ↵ect.
Soundscape Audio Signal Classification and Segmentation Using Listeners Perception of Background and Foreground Sound
TLDR
The background and foreground classification task within a musicological and soundscape context is established, and a method for the automatic segmentation of soundscape recordings based on this task is presented.
...
...