Biographical data


Me, 2013


Heikki Kallasjoki, officially. fizzie, un.

Who am I?

I am currently some sort of a software engineer (at Google) during the day, and some sort of a hacker (in the older, non-cybercrime sense) during the night.

Regarding the latter, I dabble in esoteric programming languages, among other things. The other pages here at hold a not-so-representative, not-so-up-to-date sample of the kind of things I do.

Contact information

If you do IRC in the IRCnet or the Libera Chat networks, fizzie is the name. For the latter, feel free to visit e.g. the #esolangs channel. As for email, append to the same name.

Other public profiles (in alphabetical order): flickr github Google+ YouTube

Research background

I also spent quite a while doing noise-robust speech recognition related activities at the Helsinki University of Technology Aalto University School of Science, Department of Information and Computer Science School of Electrical Engineering, Department of Signal Processing and Acoustics.

The Google Scholar profile has an autogenerated publication list that should be more or less up to date. Some highlights have been listed below as well.

PhD thesis, April 2016: Feature Enhancement and Uncertainty Estimation for Recognition of Noisy and Reverberant Speech. URN:ISBN:978-952-60-6666-0.

REVERB 2014: Heikki Kallasjoki, Jort F. Gemmeke, Kalle J. Palomäki, Amy V. Beeston, Guy J. Brown. Recognition of reverberant speech by missing data imputation and NMF feature enhancement. In Proceedings of the REVERB Workshop, Florence, Italy, May 10 2014. Later in the EURASIP Journal on Advances in Signal Processing: doi:10.1186/s13634-015-0259-1.

TASLP 2014, 22(2): Heikki Kallasjoki, Jort F. Gemmeke and Kalle J. Palomäki. Estimating Uncertainty to Improve Exemplar-Based Feature Enhancement for Noise Robust Speech Recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing, pages 368–380, volume 22, issue 2, February 2014. doi:10.1109/TASLP.2013.2292328.

Master's thesis, September 2009: Methods for spectral envelope estimation in noise robust speech recognition. (Pattern Recognition Society of Finland gave it the "best pattern recognition master's thesis in Finland 2009" award.)

Language list

As a lark, here is a list of programming languages I recall at least doing something with, roughly in inverse order of familiarity. Anything down to Prolog I could consider myself to know, up to some degree. Processor architectures in the following denote the assembly of the corresponding processor.

C, (Google) Go, Java, Python, JavaScript, Perl, C++, bash, Scheme, Haskell, MATLAB, x86(-64), Z80, C#, (Postgre)SQL, FORTH, MIPS, Q(uick)Basic, PHP, Prolog, Scala, 6502, Tcl, ARM, GLSL, Visual Basic, FORTRAN, Logo, Common Lisp, Rust, R, Erlang.

Historical background

(Very briefly.)

Born in Helsinki, Finland, in 1983. After compulsory education, went to Helsinki University of Technology to get a master's degree in computer science; major Computer and Information Science, minors Theoretical Computer Science, Telecommunications Software. While there, also got married (end of 2006). Managed to graduate in autumn 2009, just before it became the Aalto University. Spent the next few years doing graduate studies, majoring in something like Speech and Language Technology. Got hired by Google in 2015, finally finished that PhD in 2016.