Current projects
WestAI - AI Service Center West
Förderprogramm KI7_Aufbau von KI-Servicezentren
Duration: 11/2022 - 12/2025
Funded by: BMBF
Contact: Dr.-Ing. Jörg Schmalenströer
SAIL: SustAInable Life-cycle of Intelligent Socio-Technical Systems
Current systems that incorporate AI technology mainly target the introduction phase, where a core component is training and adaptation of AI models based on given example data. SAIL’s focus on the full life-cycle moves the current emphasis towards sustainable long-term development in real life. The joint project SAIL addresses both basic research ...
Duration: 08/2022 - 07/2026
Funded by: MKW NRW
TRR 318 - Constructing Explainability
In unserer digitalen Gesellschaft nehmen die algorithmischen Ansätze (wie das maschinelle Lernen) rasant an Komplexität zu. Diese erschwert es den Bürger:innen, die Assistenz nachzuvollziehen und die von Algorithmen vorgeschlagenen Entscheidungen zu akzeptieren. Als Antwort auf diese gesellschaftliche Herausforderung hat die Forschung begonnen, ...
Duration: 07/2021 - 06/2025
Funded by: DFG
TRR 318 - Technically enabled explanation of speaker traits (Subproject C06)
A voice might be described as hoarse, or it may be clear, deep, or breathy. Researchers in Project C06 are looking at issues of how different vocal traits sound, and how a voice can be represented in all of its many facets. Here, linguists and computer scientists are working to develop an intelligent system that professionals can use to explain the ...
Duration: 07/2021 - 06/2025
Funded by: DFG
Automatic transcription of conversation situations
Multi-talker conversational speech recognition is concerned with the transcription of audio recordings of formal meetings or informal get-togethers in machine-readable form using distant microphones. Current solutions are far from reaching human performance. The difficulty of the task can be attributed to three factors. First, the recording ...
Duration: 05/2021 - 12/2024
Funded by: DFG
Learning deep speech representations for phonetics research
The speech signal is a rich source of information that conveys not only linguistic but also extra/para-linguistic information, such as the speaker's identity, gender, emotional state, age, or the social status. However, those traits are hidden in complex, non-transparent variations of the speech signal, and mostly obscure to speech research. With ...
Duration: 04/2021 - 12/2024
Funded by: DFG
Explainable Feature Importance: Interpretable machine learning through game theoretic analysis of influence variables and interaction effects
Machine learning (ML) methods support the search for patterns in data and relationships between variables, e.g. in complex bio-medical systems. In this way, they can provide new insights and improve decisions in fields of action such as medical diagnostics. In addition to the quality of the models learned from the data, the trust of human experts ...
Duration: 01/2021 - 12/2024
Funded by: MKW NRW
Technically Enabled Explaining of Speaker Traits
The speech signal is a rich source of information that conveys linguistic but also what is termed para- or extralinguistic content, revealing a speaker’s identity, gender, emotional or cognitive state, age, and health. These traits have been the subject of many investigations in phonetics, but due to the high complexity of the underlying ...
Duration: 01/2021 - 12/2025
Funded by: DFG
Completed projects
Acoustic Sensor Networks Research Group
This Research Unit investigates solutions and limitations for acoustic signal processing and classification over coustic sensor networks. We aim to tackle current shortcomings and to develop a common platform which will make ASNs more adaptive to the variability of acoustic environments and sensor configurations, less dependent on supervision, and ...
Duration: 01/2017 - 12/2023
Funded by: DFG
Sound Recognition with Limited Supervision over Sensor Networks
A mismatch between training and test data statistics can result in a significant degradation of performance of machine learning systems. For sound recognition in acoustic sensor networks (ASNs) this is a significant issue because of the huge number and variability of sounds and acoustic environments, and because of the large variety of sensor ...
Duration: 01/2017 - 12/2023
Funded by: DFG
Distributed Acoustic Signal Processing over Wireless Sensor Networks
We consider an acoustic sensor network, where different applications, such as source separation and extraction, should be executed. A straightforward solution might be to transport all data to a gateway node and process it there. This is, however, not necessarily the best solution (data rate bottlenecks, large latency for big acoustic data). We ...
Duration: 01/2017 - 12/2023
Funded by: DFG
FOR 2457 – Koordinationsfonds (Teilprojekt)
Wir sind tagtäglich von einer Vielzahl von Geräuschen und anderen akustischen Ereignissen umgeben, und doch können wir uns mühelos in einer solchen Umgebung unterhalten, und die wahrgenommenen akustischen Eindrücke geben uns eine Vorstellung darüber, in welcher Umgebung wir uns gerade befinden. Ein technisches System mit ähnlichen Fähigkeiten hätte ...
Duration: 10/2016 - 06/2021
Funded by: DFG
FOR 2457 – Unsupervised Acoustic Event Detection and Scene Classification over Sensor Networks (Subproject)
For many applications of acoustic sensor networks acoustic signal extraction and enhancement is not the eventual goal but only a necessary intermediate step on the way to classify and interpret the audio signals. In this project we are going to develop acoustic event detection and acoustic scene classification methods for the interpretation of the ...
Duration: 10/2016 - 12/2021
Funded by: DFG
Contact: Janek Ebbers
Source separation and interference reduction for automatic speech recognition in dynamic acoustic environments (Transfer Project)
This project is dedicated to a holistic approach for speech enhancement, separation and recognition in an automatic house environment. Financed by the “Deutsche Forschungsgemeinschaft” (DFG) a new system is researched combining the hand-on experience from a third-party company with the recent scientific advances in speech enhancement through deep ...
Duration: 08/2016 - 12/2021
Funded by: DFG
FOR 2457 : Acoustic Sensor Network
In daily life, we are surrounded by a multitude of noises and other acoustic events. Nevertheless we are able to effortlessly converse in such an environment, retrieve a desired voice while disregarding others, or draw conclusions about the composition of the environment and activities therein, given the observed sound scene. A technical system ...
Duration: 01/2016 - 12/2021
Funded by: DFG
FOR 2457 – Scalable Audio Features for Clustering and Classification with Privacy Constraints
Ubiquitous computing and the Internet of Things will lead to a world where sensors are everywhere and huge amounts of sensor data are collected, processed, and stored. Without doubt, the aims of these sensor networks such as the support of elderly people (AAL), increasing security of public spaces, or improving the energy efficiency of buildings ...
Duration: 01/2016 - 12/2021
Funded by: DFG
Contact: Alexandru Nelus
SPP 1527 - Bayessches Lernen einer hierarchischen Repräsentation von Sprache aus gesprochener Eingabe (Teilprojekt)
Das Ziel dieses Projekts ist das Erlernen einer hierarchischen Repräsentation von Sprache alleine aus dem akustischen Sprachsignal. Auf der untersten Ebene werden die akustischen Elementareinheiten, d.h. Phoneme oder ähnliche Wortuntereinheiten, entdeckt und Modelle dafür trainiert, während auf der nächsten Ebene die lexikalischen Einheiten, d.h. ...
Duration: 01/2014 - 12/2018
Funded by: DFG
Bayes'sche Merkmalsverbesserung zur Erkennung verhallter und verrauschter Sprache bei großem Vokabular
In diesem Vorhaben sollen Verfahren zur automatischen Spracherkennung für komplexe Erkennungsaufgaben mit großem Vokabular entwickelt werden für den Fall, dass die aufgenommene Sprache durch Raumhall und additives Rauschen gestört ist. Um eine möglichst breite Einsetzbarkeit zu gewährleisten, wird dabei von lediglich einkanalig vorliegenden ...
Duration: 01/2013 - 12/2019
Funded by: DFG