Real Time Vocal Translator By Microsoft

Replies

• 

  Ankita Katdare

  They had demonstrated the similar thing at Techfest 2011.
  First, they applied a 2-D-to-3-D reconstruction algorithm frame by frame on a 2-D video to construct a 3-D training database.
  
  
  
  As per the description in this video -
  
  In training, super-feature vectors consisting of 3-D geometry, texture, and speech are formed to train a statistical, multistreamed, Hidden Markov Model (HMM). The HMM then is used to synthesize both the trajectories of geometric animation and dynamic texture. The 3-D talking head can be animated by the geometric trajectory, while the facial expressions and articulator movements are rendered with dynamic texture sequences. Head motions and facial expression also can be separately controlled by manipulating corresponding parameters. The new 3-D talking head has many useful applications, such as voice agents, telepresence, gaming, and speech-to-speech translation.