- Top left: /a i u e o/ spoken by a male speaker
- Top right: Synthetic /a i u e o/ generated by VocalTractLab, with articulatory parameters learned from the acoustics (MFCC) of the natural utterance
- Upper middle: Animation of gradual spectrographic improvement as articulatory parameters were repeatedly adjusted
- Lower middle: Animated vocal tract movements of the synthetic utterance
- Bottom: Continuous movements of individual articulators
| Original | Synthesis |
---|
Spectrogram |  |  |
---|
Sound | | |
---|
Video: Learning articulatory targets of Japanese vowels
Video: Vocal tract movement of learned articulatory targets (slow motion)
Articulatory gestures synthesized from learned articulatory targets