Data-driven 3D visual pronunciation of Chinese IPA for language learning

In the framework of intelligent aided language learning, a real-time data-driven 3D visual pronunciation system of Chinese IPA is proposed. First, a high quality articulatory speech corpus including speech and 3D articulatory data of lips, tongue and jaw movements is collected through Electro-Magnetic Articulograph; second, the 3D articulatory modeling including shape design and motion synthesis is conducted. The articulatory shape is obtained by designing a precise 3D facial model including internal and external articulators. The articulatory motion synthesis is obtained combining parameterized model and anatomical model. The system can thus illustrate the slight differences among phonemes by synthesizing both internal and external articulatory movements. The perceptual evaluation shows the suitability of the system for instructing language learners to articulate.