I engineered the data infrastructure, automated acoustic mark-up, computed acoustic features (DSP), and handled clean-up and regularization for the public release of a large-scale phonetics database. I also performed iterative data quality assessment, and offered recommendations for continuous improvement of data collection and acoustic annotation workflows. In addition, I developed experimental presentation software, managed teams of annotators and experimenters, and provided statistical analyses (parameter estimation and hypothesis competition) for our publications and conference presentations. [R, Praat, Bash, Python, Perl, LaTeX]

Designed an annotation framework, drafted detailed guidelines for annotators. Responsible for the development of conversational speech corpora for phonetic research. Designed and built a system for Hidden Markov Model automatic forced alignment of speech sounds. Conducted evaluation of the aligner with respect to human inter-annotator agreement. Wrote annotation manual, corpus manual, aligner manual. [Python, BASH, Perl, Praat, HTK, LaTeX]

Taught Japanese, Writing Systems of the World, and Languages and Cultures of East Asia

Performed various corporate and private translations of a variety of materials.