Corpus ID: 14390199

Analysis of Voice-Onset Using Active Rays and Hidden Markov Models

  title={Analysis of Voice-Onset Using Active Rays and Hidden Markov Models},
  author={O. Jesorsky and Joachim Denzler and T. Wittenberg},
In this paper we describe an approach for an automatic evaluation system for laryngoscopical image sequences. We describe how glottis segmentation in high speed camera sequences can be done by using active rays. We show that active ray contour segmentation provides a good base for useful feature calculation. Afterwards we show how hidden Markov models (HMMs) can serve for a statistical evaluation of the given feature vector sequences. The main advantage of the HMM approach is the fact, that… CONTINUE READING


Publications referenced by this paper.
An introduction to hidden Markov models
  • 3,066
  • PDF
Direct evaluation of high-speed recordings of vocal fold vibrations.
  • 98
Active Rays: A New Approach to Contour Tracking
  • 21
  • PDF
Deformation Analysis of the Vibrational Patterns of the Vocal Folds
  • 2
Estimation of Vocal Fold Vibrations Using Image Segmentation
  • 4
  • Highly Influential
Statistische Spracherkennung
  • 28
  • Highly Influential
Die Erkennungsphase in einem Dialogsystem
  • 10
Hidden Markov Models for Speech Recognition. Number 7 in Information Technology Series
  • 1990