@inproceedings{diener2019improving,
  title        = {Improving Fundamental Frequency Generation in EMG-to-Speech Conversion using a
    Quantization Approach},
  author       = {Diener, Lorenz and Umesh, Tejas and Schultz, Tanja},
  year         = 2019,
  month        = dec,
  booktitle    = {{ASRU} 2019 - IEEE Workshop on Automatic Speech Recognition and Understanding},
  doi          = {10.1109/ASRU46091.2019.9003804},
  abstract     = {We present a novel approach to generating fundamental frequency (intonation and
    voicing) trajectories in an EMG-to-Speech conversion Silent Speech Interface, based on
    quantizing the EMG-to-F0 mappings target values and thus turning a regression problem into a
    recognition problem. We present this method and evaluate its performance with regard to the
    accuracy of the voicing information obtained as well as the performance in generating plausible
    intonation trajectories within voiced sections of the signal. To this end, we also present a new
    measure for overall F0 trajectory plausibility, the trajectory-label accuracy (TLAcc), and
    compare it with human evaluations. Our new F0 generation method achieves a significantly better
    performance than a baseline approach in terms of voicing accuracy, correlation of voiced
    sections, trajectory-label accuracy and, most importantly, human evaluations.},
  url          = {https://halcy.de/cites/pdf/diener2019improving.pdf},
}