Nils Poschadel, M. Sc.
Nils Poschadel, M. Sc.
Phone
Fax
Address
Appelstraße 9a
30167 Hannover
30167 Hannover
Building
Room
Nils Poschadel, M. Sc.
-
Persönliche Informationen
Curriculum Vitae
Nils Poschadel received the M. Sc. degree in mathematics with an emphasis on numerics and optimization from the Gottfried Wilhelm Leibniz Universität Hannover in 2017. Since then, he works as a research assistant towards a doctoral degree (Dr.-Ing.) at the Institut für Kommunikationstechink (IKT) of the Gottfried Wilhelm Leibniz Universität Hannover.
Research Interests
- Machine learning based audio signal processing
- Sound scene analysis
- Direction of arrival estimation
- Acoustic parameter estimation
- Spatial audio
Teaching
- Teacher of exercise "Signale und Systeme"
- Teacher of student laboratory "Übertragungstechnik"
Awards
- Best Student Technical Paper Award, 150th Audio Engineering Society Convention, 2021. N. Poschadel et al., “Further Insights on the Influence of a Dynamic Binaural Synthesis on Speech Intelligibility in TETRA-coded Voice Communication,” in Audio Engineering Society Convention 150, 2021.
-
Publikationsliste
Konferenzbeiträge
-
(2024): Deep-Learning-based Sound Source Localization, Fortschritte der Akustik - DAGA 2024, 50. Jahrestagung für Akustik, Hannover | File |
-
(2023): Comparison of Regression and Classification Models for Multi-Source Direction of Arrival Estimation with Convolutional Recurrent Neural Networks, Fortschritte der Akustik - DAGA 2023, 49. Jahrestagung für Akustik, Hamburg | File |
-
(2023): LoCOMo: A Low-Cost Open-Source Head Motorization Kit, 155th Convention of the Audio Engineering Society (peer-reviewed full paper; accepted for publication) More info
-
(2022): Adaption of Layerwise Relevance Propagation for Audio Applications, Fortschritte der Akustik - DAGA 2022, 48. Jahrestagung für Akustik, Stuttgart | File |
-
(2022): On the impact of input scaling strategies for deep learning based DOA estimation from Ambisonics signals, ICA 2022, Gyeongju
-
(2021): Direction of Arrival Estimation of Noisy Speech using Convolutional Recurrent Neural Networks with Higher-Order Ambisonics Signals, 29th European Signal Processing Conference (EUSIPCO 2021)
DOI: https://doi.org/10.23919/EUSIPCO54536.2021.9616204 -
(2021): Multi-Source Direction of Arrival Estimation of Noisy Speech using Convolutional Recurrent Neural Networks with Higher-Order Ambisonics Signals, 29th European Signal Processing Conference (EUSIPCO 2021)
DOI: https://doi.org/10.23919/EUSIPCO54536.2021.9616002 -
(2021): CNN-based multi-class multi-label classification of sound scenes in the context of wind turbine sound emission measurements, Proceeding of the INTERNOISE 2021 More info
DOI: https://doi.org/10.3397/IN-2021-2205 -
(2021): Further Insights on the Influence of a Dynamic Binaural Synthesis on Speech Intelligibility in TETRA-coded VoiceCommunication, 150th Convention of the Audio Engineering Society (peer-reviewed full paper), online virtual conference
-
(2021): Room Geometry Estimation from Higher-Order Ambisonics Signals using Convolutional Recurrent Neural Networks, 150th Convention of the Audio Engineering Society (peer-reviewed full paper), online virtual conference
-
(2020): Localization and Categorization of Early Reflections for Estimating Acoustic Reflection Coefficients, 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP),2020
DOI: 10.1109/MMSP48831.2020.9287099 -
(2020): Machine Learning basierte Klassifikation von Außenschallszenen für Lärmmessungen an Windenergieanlagen, Fortschritte der Akustik - DAGA 2020, 46. Jahrestagung für Akustik, Hannover
-
(2020): Investigations on the Influence of a Dynamic Binaural Synthesis on Speech Intelligibility in Communication Applications, Fortschritte der Akustik - DAGA 2020, 46. Jahrestagung für Akustik, Hannover
-
(2018): Machine Learning as Digital Therapy Assessment for Mobile Gait Rehabilitation, 28th IEEE International Workshop on Machine Learning for Signal Processing, September 17-20, 2018, Aalborg, Denmark
DOI: 10.1109/MLSP.2018.8517005 -
(2017): A Dictionary Learning Based Approach for Gait Classification, 22nd International Conference on Digital Signal Processing (DSP), 23-25 August 2017
DOI: 10.1109/ICDSP.2017.8096121
Diplom-/Masterarbeiten
-
(2023): Automated Audio Captioning With Transformer, Masterarbeit, ÜT (Betreuer: Zhao Ren, Nils Poschadel)
-
(2023): Towards Automatic Heart Sound Segmentation, Masterarbeit, ÜT (Betreuer: Zhao Ren, Nils Poschadel)
-
(2022): A prototyping framework for an immersive AR authoring platform in the mobility domain, MA, ÜT (Betreuer IKT: Nils Poschadel, Stephan Preihs)
-
(2022): Direction of Arrival Estimation with Spherical Microphone Arrays using Deep Neural Networks, MA, ÜT (Betreuer: Nils Poschadel)
-
(2022): Audiosynthese von Windenergieanlagen-Schallszenen auf Basis von generativen neuronalen Netzen, MA, ÜT (Betreuer: Nils Poschadel, Stephan Preihs)
-
(2021): On the Interpretability of Deep Neural Networks for the Analysis of Spatial Sound Fields using Higher-Order Ambisonics Signals, MA, ÜT (Betreuer: Nils Poschadel, Stephan Preihs)
-
(2021): Damage Detection with Machine Learning Algorithms on the example of Port Structures, MA, ÜT (Betreuer IKT: Nils Poschadel)
-
(2020): Intelligente Auswertung von Betriebsdaten einer Werkzeugmaschine im Kleinserienbetrieb, MA, ÜT (Betreuer/in: Petra Hildebrand, Nils Poschadel)
-
(2020): Trajectory Analysis at Intersections, MA, ÜT (Betreuer/in: Stefania Zourlidou, Nils Poschadel)
-
(2019): Untersuchungen zum Einfluss einer dynamischen Binauralsynthese auf Eigenschaften der Sprachwahrnehmung in Kommunikationsanwendungen , MA, ÜT (Betreuer: Nils Poschadel, Stephan Preihs)
-
(2017): Entwicklung effizienter Methoden des Dictionary Learning zur Gangklassifizierung hochdimensionaler Sensordaten, MA, ÜT (Betreuer: S. Moghaddamnia, Javier Conte Alcaraz)
-
(2017): Verfahren der Hauptkomponentenanalyse zur multisensoriellen Gangbildanalyse, MA, ÜT (Betreuer: S. Moghaddamnia, Javier Conte Alcaraz und N. Poschadel)
Studien-/Bachelorarbeiten
-
(2020): 2020 Klassifikation urbaner binauraler Schallszenen unter Verwendung von Deep Learning, BA, ÜT (Betreuer: Nils Poschadel, Stephan Preihs)
-
(2020): Transferlernen zur Klassifizierung von Außenschallszenen im Rahmen der Lärmmessung an Windenergieanlagen, BA, ÜT (Betreuer: Nils Poschadel, Stephan Preihs)
-
(2019): Machine Learning based Head Gesture Classification, Studienarbeit, ÜT (Betreuer: Nils Poschadel)
-
(2019): Investigations on Machine Learning based Audio Coding, BA, ÜT (Betreuer: Nils Poschadel, Stephan Preihs)
-
(2019): Machine Learning basierte Audioszenenklassifikation, BA, ÜT (Betreuer: Nils Poschadel, Stephan Preihs)
Sonstiges
-
(2018): Evaluation of Machine Learning Algorithms for HRTF Individualization, Projektarbeit, ÜT (Betreuer: Song Li, Nils Poschadel)
-
-
Forschungsprojekte
-
Hooray – Evaluation der Leistungsgrenzen eines am Kopf getragenen Mikrofon-Arrays für auf Deep Learning basierende dynamische akustische SzenenanalyseLed by: Prof. Dr. Jürgen PeissigTeam:Year: 2023Funding: Deutsche Forschungsgemeinschaft (DFG), Projektnummer: 517437545Duration: 03/2023 - 02/2026
![]()
![]()
-
VIA²mobiLGenerierung virtueller interaktiver akustischer Soundszenen für eine verbesserte Audiokommunikation in mobilen LeitstellenLed by: Prof. Dr. Jürgen PeissigTeam:Year: 2017Funding: Bundesministerium für Wirtschaft und Energie (BMWi, Förderkennzeichen: ZF4298802LF7)Duration: 09/2017 - 08/2019
![]()
![]()
-
