• English
• Türkçe

Facial expressions and emotional states of a person are related since gestures and facial expressions are used to express an emotion. Recognition of the emotional state from speech signal has become an important issue due to its benefits in the domain of human-computer interaction.

Momentum has developed speech processing algorithms and tools for automatically generating speech synchronous facial expressions for 3D talking heads. The proposed system is speaker and language independent. Using the developed system, we can generate speech-driven expressional head and facial animations for applications such as computer games, e-learning, 3D agent-based assistance, etc.

PRESENTATIONS

Comparison of Phoneme and Viseme Based Acoustic Units For Realistic Lip Animation

Natural looking lip animation, synchronized with incoming speech, is essential for realistic character animation. Humans are very sensitive to the slightest glitch in the animation of the human face. Therefore, it is necessary to achieve realistic lip animation, which is synchronous with a given speech utterance…

Speech Driven Automatic Facial Expression Synthesis

Emotionally expressive talking head applications become popular due to their benefits in the domain of the human-computer interaction (E-learning, computer game, 3D agent-based assistance, etc.). For such applications it is crucial to generate speech-synchronized and natural looking animations since the talking head will interact with a human…