Thomas Niesler
University of Stellenbosch, Stellenbosch University, University of Cambridge, Cambridge University
About
I obtained my B.Eng and M.Eng degrees in Electronic Engineering from the University of Stellenbosch, South Africa in 1991 and 1993 respectively. I also hold a Ph.D. (1998) from the University of Cambridge, England on the subject of statistical language modelling for large vocabulary speech recognition. I joined the Department of Engineering, University of Cambridge, as a lecturer in 1998 and subsequently the Department of Electrical and Electronic Engineering, University of Stellenbosch, in 2000, where I have been a full Professor since 2012. My research interests lie in the areas of machine learning, pattern recognition and signal processing, with a particular emphasis on audio signals and human language technology.
Employment
-
University of Stellenbosch Full professor2012 - Present
-
University of Stellenbosch Associarte Professor2009 - 2012
-
Stellenbosch University Senior Lecturer2000 - 2009
-
Cambridge University Lecturer1998 - 2000
-
University of Cambridge Research Associate1997 - 1998
Education
-
University of Cambridge Ph.D.1994 - 1997
-
Stellenbosch University M.Eng1992 - 1993
-
Stellenbosch University B.Eng1988 - 1991
Projects & Funding
Projects & funding information is unavailable.
Publications (172)
- Learning to rumble: automated elephant call and sub-call classification, detection and endpointing using deep architectures Save
- WhaleVAD-BPN: Improving baleen whale call detection with boundary proposal networks and post-processing optimisation Save
- CACOphony: Contrastive architecture for TB cough classification Save
- Lang2Vec: language-level embeddings for robust low-resource language identification in text. Save
- Whale-VAD: Whale Vocalisation Activity Detection Save
- The sky is the limit: Evaluating the Argos Satellite Constellation’s coverage in different terrain Save
- A transformer-based voice activity detector Save
- Automatic partitioning of a code-switched speech corpus using mixed-integer programming Save
- Mathematical content browsing for print-disabled readers based on virtual-world exploration and audio-visual sensory substitution Save
- Accelerometer-based bed occupancy detection for automatic, non- invasive long-term cough monitoring Save