Automatic pre-segmentation of running speech improves the robustness of several acoustic voice measures.

@article{Bckstrm2003AutomaticPO,
  title={Automatic pre-segmentation of running speech improves the robustness of several acoustic voice measures.},
  author={Tom B{\"a}ckstr{\"o}m and Laura Lehto and Paavo Alku and Erkki Vilkman},
  journal={Logopedics, phoniatrics, vocology},
  year={2003},
  volume={28 3},
  pages={101-8}
}
In order to study vocal loading, we developed a speech analysis environment for continuous speech. The objective was to build a robust system capable of handling large amounts of data while minimizing the amount of user-intervention required. The current version of the system can analyze up to five-minute recordings of speech at a time. Through a semiautomatic process it will classify a speech signal into segments of silence, voiced speech and unvoiced speech. Parameters extracted from the… CONTINUE READING