Algorithms for extracting robust and accurate speech features and their application in clinical domain

Samples of everyday conversations are being collected and analyzed in a growing num- ber of applications, ranging from studying behavior in social psychology to clinical assess- ment of voice pathology and even cognitive function. Aside from the spoken words, the acoustic properties of speech samples can provide important cues in these applications. The goal of this study is developing novel algorithms for robust and accurate estimation of speech features and employing them to build probabilistic speech models for character- izing and analyzing clinical speech. We aim to achieve accurate and reliable estimation of voiced segments, fundamental frequency, harmonic-to-noise ratio (HNR), jitter, and shim- mer for clinical speech analysis. Towards this goal, we adopt a harmonic model (HM) of speech.