I work within the broader Speech and Audio Processing group at Idiap Research Institute, with particular focus on the conjunction of speech recognition and speech synthesis. In each case, I try to focus on physiologically plausible systems. Here is a short bio.
A (possibly incomplete) list of my patents. They are mainly US, but in practice most of these began life as either GB or Japan patents; the US ones are just easier to reference.
Other technical reports that are not commercial in confidence or published elsewhere. The list includes some MPEG submissions that made it into MPEG-7.
- BuSLR is a build system. It contains conda recipes for some speech & language software along with an experimental system based around cmake.
- SSP is a signal processing library in python. It contains, amongst other things, a feature extractor and continuous pitch estimator.
- libssp duplicates some functionality of SSP in a C++ library.
- ISS is a framework for building and evaluating ASR models.
- Juicer is a collection of ASR decoders. It is not currently under active development; most of the functionality is available in Kaldi. However,
- I wrote and (infrequently) maintain Tracter, a data-flow framework that forms the feature acquisition mechanism of Juicer. Tracter wraps several other packages, including libssp.
Other work is on my GitHub page.
Since May 2019, I teach the course “Fundamentals of Statistics for AI” with David Ginsbourger and colleagues for UniDistance. A while ago now, I held a lecturer position at EPFL, and taught a course on Speech Signal Processing.
Look at the username above and add
@idiap.ch. It’ll probably get
here. Otherwise try the
Idiap contact page.
For a long while I wasn’t on facebook and the like. I’ve since bought into the social networking world, including LinkedIn. Some more are below; finding the others is left as an exercise for the user.