Member Login

JCal Pro Mini-calendar

October 2019 November 2019 December 2019
Mo Tu We Th Fr Sa Su
Week 44 1 2 3
Week 45 4 5 6 7 8 9 10
Week 46 11 12 13 14 15 16 17
Week 47 18 19 20 21 22 23 24
Week 48 25 26 27 28 29 30

Current Time

The time is 20:01:09.
Jorge Dávila Chacón Print E-mail
Jorge Davila Chacon
 

Contact Details

Department of Informatics
Hamburg University
Vogt-Kölln-Straße 30
22527 Hamburg, Germany

Phone: +49 40 42883-2535
Fax: +49 40 42883-2515
Room: F-216
eMail: This e-mail address is being protected from spam bots, you need JavaScript enabled to view it
Supervisor: Prof. Dr. Stefan Wermter

Short Biography

Feb 2009 – July 2011: MSc Artificial Intelligence
Rijksuniversiteit Groningen (The Netherlands)
"Visual-topological Mapping: An approach for indoor robot navigation"

Sep 2002 – Dec 2008: BEng Mechanics and Electricity (Double Degree)
Benemérita Universidad Autónoma de Puebla (Mexico)

 

Research Interests

- Artificial Intelligence
- Machine Learning
- Neural sound localization for speech processing based on the inferior colliculus

Current Projects

The auditory system is one of the senses that can inform us about the spatial location of distant events. Sounds can provide information comparable to visual stimuli in scenarios where vision is impeded. Hence, localisation of sound events in nature is essential for survival and can be crucial for communication.

It is equally important for autonomous robots to localise dynamic sound sources, e.g. to avoid collisions. Furthermore, the processes underlying spatial hearing can be used for segregation of multiple speakers [1] and aid human-robot interaction.

Sound spatial cues originate from the geometrical properties of our head, ears and torso, which we mimic using a humanoid robot. On the computational side, there are plausible reasons for pursuing a bio-inspired approach to robotic sound source localisation. Firstly, natural systems display the most robust performance at present. Secondly, time-dependent encoding of spatial cues is intrinsic to the nature of sound. For these reasons, arti ficial spiking neural networks were chosen for modelling the midbrain areas relevant for spatial hearing [2].

The current understanding of neural sound processing in mammals reveals the importance of the inferior colliculus for the integration of spatial cues [3]. This process alone resembles multi-sensory integration occurring in higher cognitive levels. Therefore, the underlying neural processes for sound source localisation may be further understood if examined by multimodal interaction theories.

We pursue a multimodal approach to the long standing Cocktail Party problem, and sound source localisation is an essential ingredient in such enterprise [4].


[1] Roman, N., Wang, D.L. and Brown, G.J.: Speech segregation based on sound localisation. The Journal of the Acoustical Society of America (2003)
[2] Liu, J., Perez-Gonzalez, D., Rees, A., Erwin, H. and Wermter, S.: A biologically inspired spiking neural network model of the auditory midbrain for sound source localisation. Elsevier, Neurocomputing (2010)
[3] Schnupp, J., Nelken, I. and King, A.: Auditory neuroscience: Making sense of sound. The MIT Press (2011)
[4] Even, J., Heracleous, P., Ishi, C. and Hagita, N.: Multi-modal front-end for speaker activity detection in small meetings. IEEE, International Conference on Intelligent Robots and Systems (2011)

Previous Projects

Feb 2010 – Aug 2010: Research Internship. Development of an indoor visual-topological navigation system for a biped robot (Lyon, France)
- Institut National de la Santé et de la Recherché Médicale (INSERM)
- Stem-Cell and Brain-Research Institute
- Cortical Networks for Cognitive Interaction Team

Mar 2010 – Jun 2011: RoboCup@Home Tournament.
- German Open (Magdeburg)
- Iran Open (Teheran)
- World cup (Singapore)


Publications

J. Davila-Chacon, J. Twiefel, J. Liu, S. Wermter. "Improving Humanoid Robot Speech Recognition with Sound Source Localisation". International Conference on Artificial Neural Networks, 2014.

J. Davila-Chacon, S. Magg, J. Liu, S. Wermter. "Neural and Statistical Processing of Spatial Cues for Sound Source Localisation". International Joint Conference on Neural Networks, 2013.

J. Davila-Chacon, S. Heinrich, J. Liu, S. Wermter. "Biomimetic Binaural Sound Source Localisation with Ego-Noise Cancellation". International Conference on Artificial Neural Networks, 2012.

J. Bauer, J. Davila-Chacon, E. Strahl, S. Wermter. "Smoke and Mirrors—Virtual Realities for Sensor Fusion Experiments in Biomimetic Robotics". IEEE International Conference on Multisensor Fusion and Information Integration, 2012.

J. Davila-Chacon. "Neural Sound Source Localisation for Speech Processing Based on the Inferior Colliculus". Proceedings of the Joint Workshop of the German Research Training Groups in Computer Science, 2012.

J. Davila-Chacon, T. van Elteren, B. Hickendorff, H. van Hoof, E. Jansen, S. knuijver, C. Lier, P. Neculoiu, A. Nolte, C. Oost, V. Richthammer, F. Schimbinschi, M. Schutten, A. Shantia, R. Snijders, E. van der Wal, T. van der Zant. "BORG - The RoboCup@Home team of the University of Groningen Team Description Paper". RoboCup@Home Technical Description Papers: Germany - Iran, 2011.

P. Ford Dominey, T. van der Zant, S. Lallee, A. Jouen, X. Hinaut, A. Weitzenfeld, H. van Hoof, J. Davila-Chacon. "Cooperative Human Robot Interaction with the Nao Humanoid: Technical Description Paper for the Radical Dudes". RoboCup@Home Technical Description Papers: Germany - Singapore, 2010.





Last Updated ( Tuesday, 22 July 2014 )