Recent Highlighted Public Talks

Older Public Talks

2014

• Gaussian process approximations for audio feature extraction presented at the workshop on Feature Extraction using Gaussian Processes, Sheffield.
• Gaussian process approximations for time-series presented at the Gaussian Process Summer School, Sheffield.
• Auditory scene analysis and the statistics of natural sounds presented at the Bernstein conference, Goettingen, Germany.
• Connecting the statistics of natural sounds to signal processing and auditory scene analysis presented at the Institute of sound and vibration research, University of Southampton.
• Unifying signal processing and machine learning presented at Microsoft Research, Cambridge.

2013

• Auditory scene analysis and the statistics of natural sounds presented at the Listening in the Wild Workshop, Queen Mary University, London, 2013. Click here to see a video of the talk.
• An introductory tutorial on Gaussian Processes presented at the Sheffield Gaussian Process Summer School June, 2013
• Modulation cascades, sound textures, and mid-level audition, presented at the British Neuroscience Association Conference. The talk included two demonstration sounds: samples from the forward model (slides 30-45) and audio texture demo (slide 46).

2012

• Machine learning for audio neuroscience, presented at the Cognition and Brain Sciences Unit.
• New views of the Kalman Filter connect machine learning, signal processing, and system identification, presented at the European Research Network for System Identification workshop.
• A brief introduction to Bayesian inference, presented at the ACCN summer school in Poland.
• Natural scene statistics and the properties of the visual system, presented at the ACCN summer school in Poland.
• A new 15 minute tutorial talk on Gaussian Processes and connections to signal processing and computer vision, presented at the Engineering Division F conference
• A brief overview of my audio research presented to Oxford Engineering Department
• A brief overview of my vision research presented to Cambridge Engineering Department

2011

• Decomposing signals into a sum of AM-FM sinusoids using probabilistic inference. Presented at the Computational Audition Workshop, HWK - Institute for Advanced Study, Northern Germany.

2010

• Probabilistic Auditory Scene Analysis talk Presented at the Computational Audition Workshop, Gatsby Unit, UCL, London. (For stimuli see here.)
• Probabilistic amplitude demodulation talk Invited Presentation at ICASSP, Dallas, Texas.

2009

• Probabilistic Auditory Scene Analysis talk Presented at the Auditory Group Clinical Laboratory, Newcastle University Medical School.

2008

• Probabilistic Auditory Scene Analysis talk Presented at the Gordon Research Conference Sensory coding and the natural environment.
• Two problems with Variational Expectation Maximisation in Time-Series models paper, technical report, and talk. Presented at the Newton Institute, Cambridge, in the workshop on Inference and Estimation in Probabilistic Time-Series Models. A video of the talk is available here.
• On sparsity and overcompleteness in image models talk presented at the Inference group, Cambridge.

2007

• Probabilistic Amplitude Demodulation talk , video and paper presented at Music Brain and Cognition Workshop, NIPS Workshops, Whistler. (Identical to ICA 2007.)
• Probabilistic Amplitude Demodulation talk and paper presented at ICA2007, London. Won best student paper award. (Talk also presented at the Gatsby annual review, 10/10/2007)
• Extracting the speaker vocal tract length from speech data: Inference of Vocal Tract Length from vowel formants, R. Turner, T. Walters and R. Patterson , talk presented at the Size Meeting, CNBH, Cambridge
• On Sparsity and Overcompleteness in Image Models: talk the cortical processing meeting, Budapest.
• Modeling Natural Sounds with Modulation Cascade Processes: Amplitude modulation, frequency modulation, probabilistic STFTs and Gaussian modulation cascade models presented at the Gatsby-ENS meeting in London.
• Modeling Natural Sounds with Modulation Cascade Processes: Algorithms for Probabilistic Signal processing including demodulation (AM and FM) and STFTs presented to the Signal Processing and Communications Laboratory, Cambridge.
• Generative models for amplitude modulation: Algorithms for Probabilistic Amplitude Demodulation presented to the Inference group, Cambridge, 2007.

2006

• Advances in Models for Acoustic Processing NIPS workshop, Vancouver talk and paper: 'Modeling Natural Sounds with Gaussian Modulation Cascade Processes', R. Turner and M. Sahani 2006
• Extracting the speaker vocal tract length from speech data: Inference of Vocal Tract Length from vowel formants, R. Turner, T. Walters and R. Patterson , talk presented at the CNBH, Cambridge