Welcome to Vir2elle
Vir2elle is a synthetic agent that can produce video-realistic speech animations.
Vir2elle's realistic apperance stems from the so-called "image-based" or "sample-based" approach.
Sample images of facial parts are first collected during a training session.
The subject is recorded using a standard video camera while speaking a corpus of training sentences.
Each recorded video frame is labeled with its phonetic content using a Phoneme Aligner.
The data is then compressed and stored in a "model" file.
The creation of the model file is a one-time operation and
Vir2elle is subsequently able to produce ANY speech animation from the model file.
Vir2elle uses concatenative synthesis to reassemble stored images of facial parts into a new animation
that is lip-synchronized with the audio track.
Vir2elle requires, as input, a "string of phonemes" to produce an animation.
Such data is available from off-the-shelve Text-To-Speech (TTS) synthesizers. Alternatively,
a recorded audio track can be phonetically labeled to produce even more realistic and
convincing animations.
To produce emotions and facial expressions, Vir2elle accepts special markers called emoticons within the text input.
The insertion of emotions happens during pauses in the speech.
Parameterized emotion snippets are inserted and can be adjusted for duration and intensisty.
The demo system available on this server lets the user type in free text and receive
the corresponding speech animation in the form of a downloaded video file.
The file format is Windows Media Video (.wmv) version 8.
It is compressed down to about 100 Kbits/sec.
The user can select the language from the list of available TTS (Text-To-Speech) voice fonts.
Alternatively, Vir2elle can produce
animations from a phonetically labeled audio track. This functionality is also
demonstrated in the demo system where the user can select among a list of recorded audio tracks.
-- News -- News -- News --
Make Vir2elle speak! [CLICK HERE FOR THE DEMO]
High-Res Vir2elle (320x240) [CLICK HERE FOR THE DEMO]
-- Links -- Links -- Links --