Reconstruction of vocal tract based on multi-source image information

At present, a variety of instruments recording the articulation have its own pros and cons. None is able to record the data containing all the information of articulators. For example, ultrasound system can obtain main surface information of the tongue, but the images are noisy and cannot record tongue tip under some cases. While the EMA system can precisely record trajectory data of the key points associated with attached sensors on the tongue surface. Therefore, we use EMA and ultrasound simultaneously as a complementary. In this paper, we will use the ultrasound system and the EMA system to record the tongue´s movement. We obtain the ultrasound images and the synchronous audio by the ultrasound system; the EMA system is used to collect the EMA data and the synchronous audio. We register and match the ultrasound images and the EMA data by the audio files. And we integrate spatially the ultrasound images and the EMA data of each time point.