Validation of the Non-Intrusive Codebook-Based Short Time Objective Intelligibility Metric for Processed Speech

Charlotte Sørensen, Jesper B. Boldt, Mads G. Christensen


In recent years, objective measures of speech intelligibility have gained increasing interest. However, most speech intelligibility metrics require a clean reference signal, which is often not available in real-life applications. In a recent publication, we proposed a method, the Non-Intrusive Codebook-based Short-Time Objective Intelligibility (NIC-STOI) metric, which allows using an intrusive method without requiring access to the clean signal. The statistics of the reference signal is estimated as a combination of predefined codebooks that best fit the degraded signal by modeling the speech and noisy spectra. In this paper, we perform additional validation of the NIC-STOI in more diverse noise condition as well as for speech processed non-linearly with binary masks, where it is shown to outperform existing non-intrusive metrics.


 DOI: 10.21437/Interspeech.2019-1625

Cite as: Sørensen, C., Boldt, J.B., Christensen, M.G. (2019) Validation of the Non-Intrusive Codebook-Based Short Time Objective Intelligibility Metric for Processed Speech. Proc. Interspeech 2019, 4270-4274, DOI: 10.21437/Interspeech.2019-1625.


@inproceedings{Sørensen2019,
  author={Charlotte Sørensen and Jesper B. Boldt and Mads G. Christensen},
  title={{Validation of the Non-Intrusive Codebook-Based Short Time Objective Intelligibility Metric for Processed Speech}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={4270--4274},
  doi={10.21437/Interspeech.2019-1625},
  url={http://dx.doi.org/10.21437/Interspeech.2019-1625}
}