The analysis of the articulatory movements allows investigating the kinematic characteristics of some speech disorders. However, the methodologies most used until now, as electromagnetic articulography and optoelectronic systems, are expensive and intrusive which limit their use to specialized laboratories. In this work, we use a completely markerless and low-cost technique to study lip movements during a syllable repetition task. By means of a Kinect-like and an existing face tracking algorithm, we are able to track the movements of the lower lip, testing the performances against a reference method (marker-based optoelectronic system). Good results were obtained in terms of RMSE for the tracking of the lower lip during the repetitions. Some kinematic measures, as opening and closing velocities and accelerations, were also computed. Despite the limitations in terms of image resolution, these results are very promising in the optic of developing a new markerless system for studying speech articulation.
Evaluating a markerless method for studying articulatory movements: Application to a syllable repetition task
Bandini A.;
2015-01-01
Abstract
The analysis of the articulatory movements allows investigating the kinematic characteristics of some speech disorders. However, the methodologies most used until now, as electromagnetic articulography and optoelectronic systems, are expensive and intrusive which limit their use to specialized laboratories. In this work, we use a completely markerless and low-cost technique to study lip movements during a syllable repetition task. By means of a Kinect-like and an existing face tracking algorithm, we are able to track the movements of the lower lip, testing the performances against a reference method (marker-based optoelectronic system). Good results were obtained in terms of RMSE for the tracking of the lower lip during the repetitions. Some kinematic measures, as opening and closing velocities and accelerations, were also computed. Despite the limitations in terms of image resolution, these results are very promising in the optic of developing a new markerless system for studying speech articulation.File | Dimensione | Formato | |
---|---|---|---|
2015_Bandini_MAVEBA.pdf
solo utenti autorizzati
Tipologia:
PDF Editoriale
Licenza:
Copyright dell'editore
Dimensione
2.52 MB
Formato
Adobe PDF
|
2.52 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.