Talks:
Asilomar Conference on Signals, Systems, and Computers, Lin Ye, Gerald Schuller, Muhammad Imran: "Instrumental timbre transfer based on disentangled representation of timbre and pitch", Oct. 27th - Oct. 30th, 2024
Repository link: https://github.com/TUIlmenauAMS/timbre-transfer
Asilomar Conference on Signals, Systems, and Computers, Gerald Schuller, Muhammad Imran: "A psycho-acoustic loss function based on a psycho-acoustic model", Oct. 27th - Oct. 30th, 2024
Repository link: https://github.com/TUIlmenauAMS/PsychoacousticLoss
Gerald Schuller: "Report on the 2024 Asilomar Conference on Signals,Systems, and Computers Special Session on Perceptual and Higher Level Loss and Distance Functions for Audio and Acoustics", Stanford Universites Center for Computer Research in Music and Acoustics (CCRMA), October 31, 2024.
Report https://github.com/TUIlmenauAMS/PsychoacousticLoss/blob/main/asilomar2024_report.pdf
Gerald Schuller: "Report on the 2024 Asilomar Conference on Signals,Systems, and Computers Special Session on Perceptual and Higher Level Loss and Distance Functions for Audio and Acoustics", October 31, 2024.
Cambridge, MA, SANE 2024 - Speech and Audio in the Northeast, Poster Presentation at Speech and Audio in the Northeast Workshop, Gerald Schuller: Fast Black-Box Optimizers for Low Delay Audio Source Separation, October 2024
Poster and corresponding software and paper can be found in our Github repository: https://github.com/TUIlmenauAMS/BlackBoxOptimizerSPcomparison
New York University, Tandom School of Engineering, NYC, USA, Gerald Schuller: Fast Black-Box Optimizers for Low Delay Audio Source Separation
Presentation BlackBoxOptim-Presentation.pdf
ICASSP 2024 (HSCMA 2024), Seoul, Korea, Gerald Schuller: Fast Black-Box Optimizers for Low Delay Audio Source Separation
Poster BlackBoxOptim-Poster.pdf
Paper BlackBoxOptim-Paper.pdf
Talks for PyBerlin
Roomba Robot with camera (Github page with description and software)
Corona computations (Github page)
Georgia Institute of Technology, Gerald Schuller: "Perceptually Motivated Audio Loss Functions for Deep Learning", March 26, 2024
Harvard University, Gerald Schuller: "Python Programs and Book for Building an Audio Coder and for Deep Learning for Audio", September 23, 2022
Johns Hopkins University, Gerald Schuller: "https://github.com/TUIlmenauAMS/LowDelayMultichannelSourceSeparation_Random-Directions_Demo", September 29, 2022
University of California at Berkeley, Gerald Schuller: "https://github.com/TUIlmenauAMS/Audio-Processing-Resources", October 4, 2022
Stanford University, Gerald Schuller: "https://github.com/TUIlmenauAMS/Audio-Processing-Resources", October 7, 2022
PyBerlin, Gerald Schuller: "Using Deep Language Models with Txtai and DiscoArt", August 24, 2022
PyBerlin, Gerald Schuller: "Corona Virus Computations and Plots using Python Notebooks in Google Colab", April 2021
PyBerlin 15 Meetup, Gerald Schuller: "Building and Programming Home Robots with Raspberry Pi and Python", April 23, 2020.
"A FAST STEREO AUDIO SOURCE SEPARATION FOR MOVING SOURCES", Adobe Inc., San Francisco, November 7, 2019
G. Schuller: conference talk on "Neural Networks and Sparse Coding from the Signal Processing Perspective", SpaRTaN-MacSeNet Spring School on Sparse Representation and Compressed Sensing, April 2016, Ilmenau, Germany (Python examples)
Invited Plenary Talk: G. Schuller: "Parametric Audio and Video Processing", IEEE Conference on Electronics, Computing, and Communications Technologies (CONECCT), Bangalore, India, Januar 6-7, 2014
Organisation of the workshop "Next Generation Audio Communications", and talk, at the 119th Audio Engineering Society (AES) Convention, New York, Oktober 7-10, 2005
G. Schuller: "Low Delay Audio Coding for Communications Applications", invited talk, DIMACS Working Group on Data Compression in Networks and Applications, Rutgers University, New Jersey, March 18-20, 2002
