The Chair of Intelligent Maintenance Systems focuses on developing intelligent algorithms to improve performance, reliability and availability of complex industrial assets and making the maintenance more cost efficient. Our research focuses on deep learning, domain adaptation, hybrid approaches (combing physical performance models and deep learning algorithms), and deep reinforcement learning. The data we are typically dealing with comprises heterogeneous multivariate time series data of different types, with different sampling rates and different degrees of uncertainties.
In recent years, the popularity of acoustic monitoring has grown rapidly thanks to recent advances in acoustic sensor technology, which are now cheap, non-invasive and easy to install. Thereby, genuine interest from the industry is emerging since the sound emitted by a machine during operation can be indicative of the process quality and of the machine health. In addition, acoustic monitoring has several other applications, like event detection for multimedia system or wildlife surveying for ecological and behavioral studies.
However, the monitoring task from audio recordings stays complex because it consists to analyze huge, noisy high-frequency signals. It is difficult to build a monitoring system that automatically detects relevant features in the recordings and that is also robust to several operating conditions.
For this project, we aim to use recent advances in artificial intelligence and deep learning to overcome these limitations.
The successful applicant will drive the research in the field of deep learning applied to time series data from audio recordings. The position includes following responsibilities:
We are looking for a PhD student with a strong analytical background and an outstanding Msc degree in Engineering, Computer Science, Physics, Applied Mathematics, or a related field. The candidate should have a proven experience in deep learning and in the application of deep learning to solve a real-world problem. The candidate should have good programming skills in Python, in particular Tensorflow or Pytorch and have knowledge in signal processing (Wavelet/spectral analysis, time series processing). Experience in audio signal processing is an advantage but is not a prerequisite. Professional command of English (both written and spoken) is mandatory. German is an advantage. We expect the candidate to be self-driven with strong problem solving abilities and out-of-the-box thinking. The duration of the PhD position is foreseen for three years.
We look forward to receiving your online application until June 30, 2021 including:
Only COMPLETE applications containing ALL the required documents will be considered. Please note that we exclusively accept applications submitted through our online application portal. Applications via email or postal services will not be considered.
The review of applications will continue until the position is filled, with the position to start in early fall 2021.
For more information about the chair please visit: www.ims.ibi.ethz.ch. Questions regarding the position should be directed to Prof. Dr. Olga Fink by email email@example.com (no applications).
|Title||PhD Student in Deep Learning for Acoustic Monitoring|
|Job location||Rämistrasse 101, 8006 Zurich|
|Published||May 1, 2021|
|Job types||PhD  |
|Fields||Algorithms,   Programming Languages,   Computer Engineering,   Applied Mathematics,   Computational Sciences  |