ISCA Archive Interspeech 2012
ISCA Archive Interspeech 2012

Automatic measurement of positive and negative voice onset time

Katharine Henry, Morgan Sonderegger, Joseph Keshet

Previous work on automatic VOT measurement has focused on positive-valued VOT. However, in many languages VOT can be either positive or negative (“prevoiced”). We present a discriminative algorithm that simultaneously decides whether a stop is prevoiced and measures its VOT. The algorithm operates on feature functions designed to locate the burst and voicing onsets in the positive and negative VOT cases. Tested on a database of positive- and negative-VOT voiced stops, the algorithm predicts prevoicing with >90% accuracy, and gives good agreement between automatic and manual measurements.

Index Terms: voice onset time, automatic phonetic measurement, discriminative methods, structured prediction

doi: 10.21437/Interspeech.2012-264

Cite as: Henry, K., Sonderegger, M., Keshet, J. (2012) Automatic measurement of positive and negative voice onset time. Proc. Interspeech 2012, 871-874, doi: 10.21437/Interspeech.2012-264

  author={Katharine Henry and Morgan Sonderegger and Joseph Keshet},
  title={{Automatic measurement of positive and negative voice onset time}},
  booktitle={Proc. Interspeech 2012},