Andrew Mitchell is a Research Fellow in urban soundscape modelling at University College London (UCL). His research interests include soundscape analysis and visualisation, machine learning, and human perception of complex sounds. Andrew has been awarded two PhD and one Post-doctoral Enrichment Awards from The Alan Turing Institute and spent a month in early 2022 as a visiting research fellow at Stockholm University. His ongoing projects include the Soundscape Indices (SSID) Horizon 2020 project, Soundscapy, Deep Learning Techniques for noise Annoyance detection (DeLTA), AI for Urban Soundscape Enhancement (AI USE), the Catalogue of Soundscape Interventions (CSI), and the Soundscape Attributes Translation Project (SATP).
Andrew is also the host of The Rest is Just Noise, a monthly podcast exploring the relationship between sound and our cities. Each episode, Andrew and his co-hosts and colleagues Dr Francesco Aletta and Dr Tin Oberman speak with researchers and experts from a wide range of backgrounds about their work in urban sounds and sound perception.
Download my CV.
PhD in Environmental Design (ongoing), 2022
UCL
BSc. Physics & Music, 2015
Cardiff University
This study first examines the methods presented in ISO 12913 for analysing and representing soundscape data by applying them to a large existing database of soundscape assessments. The key issue identified is the inability of the standard methods to summarise the soundscape of locations and groups. The presented solution inherently considers the variety of responses within a group and provides an open-source visualisation tool to facilitate a nuanced approach to soundscape assessment and design. Several demonstrations of the soundscape distribution of urban spaces are presented, along with pro- posals for how this approach can be used and developed.
The unprecedented lockdowns resulting from COVID-19 in spring 2020 triggered changes in human activities in public spaces. A predictive modeling approach was developed to characterize the changes in the perception of the sound environment when people could not be surveyed. Building on a database of soundscape questionnaires (N = 1,136) and binaural recordings (N = 687) collected in 13 locations across London and Venice during 2019, new recordings (N = 571) were made in the same locations during the 2020 lockdowns. Using these 30-s-long recordings, linear multilevel models were developed to predict the soundscape pleasantness (R2 = 0:85) and eventfulness (R2 = 0:715) during the lockdown and compare the changes for each location. The performance was above average for comparable models. An online listening study also investigated the change in the sound sources within the spaces. Results indicate (1) human sounds were less dominant and natural sounds more dominant across all loca- tions; (2) contextual information is important for predicting pleasantness but not for eventfulness; (3) perception shifted toward less eventful soundscapes and to more pleasant soundscapes for previously traffic-dominated loca- tions but not for human- and natural-dominated locations. This study demonstrates the usefulness of predictive modeling and the importance of considering contextual information when discussing the impact of sound level reductions on the soundscape.
As part of the Soundscape Indices (SSID) research team, I am primarily responsible for the development of machine learning models, data management and publication, and industry collaborations. My projects and appointments include:
Soundscapy
an open-source Python package for soundscape data analysis and visualisationProvide tuition & marking support, content development, and instruct students for the following courses:
As part of an extensive industry collaboration, my role was to provide leading edge insights from modern research on soundscapes and sound perception to better inform the design of the built environment. I also lead the development of a unique and innovative method for assessing the sound experience of building occupants and worked toward designing a comprehensive soundscape rating metric. This project required:
Primary research responsibility is to investigate machine learning and regression modelling of soundscapes based on acoustical and non-acoustical factors. As a team member on the SSID project group, practical responsibilities include: