Master Thesis »deep Learning Based Detection and - Ilmenau, Deutschland - Digital Media Technology

Beschreibung

The Fraunhofer Institute for Digital Media Technology IDMT is part of the Fraunhofer-Gesellschaft.

Headquartered in Ilmenau, Germany, the institute is internationally recognized for its expertise in applied electroacoustics and audio engineering, AI-based signal analysis and machine learning, and data privacy and security.

At the headquarters, on the campus of "Technische Universität Ilmenau" researchers work on technologies for robust, trustworthy AI-based analysis and classification of audio and video data.

These are used, among other things, to monitor industrial production processes, but also in traffic monitoring or in the media context, for example when it comes to automatic metadata extraction and audio manipulation detection.

Another focus is the development of algorithms for the areas of virtual product development, intelligent actuator-sensor systems and audio for the automotive sector.

There are currently around 70 employees working at Fraunhofer IDMT in Ilmenau.

In the group Semantic Music Technologies at the Fraunhofer IDMT, one of the main research focuses is on extracting meaningful information, identifying patterns, and making sense of complex acoustic recording.

For this purpose, methods from audio signal processing and machine learning are often combined.


What you will do
Marine mammals play a crucial role in marine ecosystems and contribute to the balance and health of the oceans.

Changes in their populations and migration patterns may indicate shifts in their environment, including variations in food availability, water temperature, or the presence of pollutants.

Bioacoustic research investigates underwater soundscapes to identify different animal species.

The result of these investigations allows to develop strategies to preserve the biodiversity of marine ecosystems and to protect endangered species.

The overall goal of this thesis is to develop a deep learning-based system for detecting and classifying typical vocalizations of marine mammals based on recordings of passive acoustic monitoring (PAM) devices like hydrophones.

Objectives

• Literature review on bioacoustics research for marine mammal detection and classification
• Review of available research datasets (Starting point: [1])
• Dataset analysis and preprocessing [2, 3]
• Study two state-of-the-art sound event detection models (e.g. Slow-Fast Auditory Streams [4], Audio Spectrogram Transformer [5]) for marine mammal detection & classification
• Investigate different data augmentation methods such as MixUp, SpecAugment
• Test transfer-learning approaches, where the models are pre-trained on general-purpose audio classification using the AudioSet dataset (will be made available) or object detection in natural images using the ImageNet dataset
• Document results & write thesis

References
[2]


BEANS:
The Benchmark of

Animal Sounds:
[ ]


BEANS:
The Benchmark of Animal Sounds )

[3] Acoustic Detection of Humpback Whales Using a Convolutional Neural Network - Google Research Blog

[4] E. Kazakos, A. Nagrani, A. Zisserman and D. Damen, "Slow-Fast Auditory Streams for Audio Recognition," ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada, 2021, pp

[5] Yuan Gong, Yu-An Chung, and James Glass, "


AST:
Audio Spectrogram Transformer," in Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), Brno, Czech Republic, 2021, pp


What you bring to the table

For this thesis topic, a solid understanding of the fundamentals of audio signal processing, machine learning, and deep learning, along with experience in using of version control systems such as Git is highly desirable.

What you can expect
- exciting market-related topics with complex issues to be solved - you can be actively involved in shaping the future
- challenges at a high level - on top we offer you excellent opportunities for professional and technical trainings
- space to also implement your own ideas, such as in our quarterly open-topic idea contest
- an excellent technical infrastructure
- renowned partners and customers who work closely with you to develop the technologies of tomorrow
- a very good work-life balance thanks to flexible working hours, a co-child office, the option of digital childcare in case of daycare shortages, and the possibility of mobile working, because family comes first - we know that
- an open-minded and interested team, a tolerant and familiar atmosphere as well as regular team events
- good transport connections and proximity to the state capital Erfurt
- attractive special offers as part of Fraunhofer corporate benefits with numerous enterprise partners
- new work and diversity are not just empty buzzwords, but an integral part of our corporate culture

With its focus on developing key technologies that are vital for the future and enabling the co