Ideas, concepts, developments, reports, code and more
The project's publications can be found here.Sound sensors for smart cities and assistive technology
Mark Plumbley gave a talk at the Connected Places Catapult in London on how sound sensors could support smart cities and assistive technology :
DCASE 2018 Workshop - Looking back
Mark Plumbley and Christian Kroos served as the General Chairs for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 Workshop. The two-day international workshop took place at the Living Planet Centre of the World Wide Fund for Nature (WWF) in Woking, Surrey, UK. It attracted significant interest, almost doubling the number of participants from the year before and reaching the capacity limit of the venue (150 participants, 62% from academia, 38% from industry).
Sounds and the city – Acoustic detection of open windows in indoor environments
Christian Kroos and Yin Cao together with Phil Coleman from the Institute of Sound Recording have been awarded one of University of Surrey’s Urban Living Award grants.
MSoS Challenge: Results published
The Making Sense of Sounds challenge results have been published.
MSoS Challenge: Extension of submission deadline
The deadline for submissions to the Making Sense of Sounds challenge has been extended to 5. November 2018.
MSoS Challenge: Baseline added
We added a strong state-of-the-art deep learning baseline in the Making Sense of Sounds. Details can be found here.
MSoS Challenge: Evaluation data released and submission opened
The Evaluation data set of the Making Sense of Sounds challenge has been released and the submission system is now open.
MSoS Data Challenge submission updated
More information about the submission to the Making Sense of Sounds data challenge was provided with this update.
Making Sense of Sounds Data Challenge opened
Today the Making Sense of Sounds data challenge was opened with the release of the development data set.
Talk at Research Software Engineer (RSE) event: 'Here be dragons'
The project’s research software developer Christian Kroos gave a presentation at the RSE event ‘What is a Research Software Engineer?’ at the University of Surrey.
DCASE 2017 challenge success
Yong Xu, Qiuqiang Kong, Wenwu Wang and Mark Plumbley won the 1st prize in Task 4, ‘large-scale weakly supervised sound event detection for smart cars’, Subtask A, ‘audio tagging’ in the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2017). The DCASE challenge constitutes the most important challenge in the non-speech audio domain. It is organised by Tampere University of Technology, Carnegie Mellon University and INRIA and sponsored by Google and Audio Analytic. Because of its unique standing, the best players in the field participate such as CMU, New York University, Bosch, USC, TUT, Singapore A*Star, Korean Advanced Institute of Science and Technology, Seoul National University, National Taiwan University and CVSSP.
DCASE 2016 Challenge: Random system performance in sound event detection in real life audio
In this report we describe the creation of a random, data-blind system to provide a random baseline for Task 3 (sound event detection in real life audio) in the DCASE 2016 challenge. Particular attention is paid to the results of two sound events occurring in the residential area scene, one very rare, the other very frequent. The relatively good performance of the random system in comparison to the results of the proper detection systems shows the difficulty of Task 3 given the current state-of-the-art sound detection methods.