Articulation-disordered speech has a co-articulation effect between phonemes.
Due to chunking, there is also a co-articulation effect at the beginning and the end of each analysed phone sample.
In these experiments, the optimal value of the co-articulation parameter was t c = 3, which corresponds to a co-articulation timea of 100 ms. Compared to the previous experiment, where a reduced vocabulary (digits utterances) was employed, the number of states needed in this case increases considerably due to the fact that a larger vocabulary is being represented by the AV-HMM.
As discussed above, these early differences mostly likely reflect an effect of co-articulation caused by phonetic differences already present in the first syllable of different words rather than an early onset of the N400 word effect.
We consider that this is because slow queries usually posses a clearer pronunciation, and less co-articulation, than faster (medium and fast) queries.
All synthesized vowel tokens were spliced in the middle of the same natural d_t frame that was taken from a naturally produced /dut/ token to avoid anticipatory co-articulation, which refers to influences preceding segments can have on the target phoneme (Fowler and Saltzman 1993).
It must be noted that the system has a constant time delay to take into account the co-articulation in the audio-visual features.
The visual speech synthesis comprises the tasks of model training, animation control, and co-articulation modelling.
In all the cases, the co-articulation parameter was set to t c =3, which proved to be the optimal value in the given range.
This combination of number of states, number of mixtures and co-articulation parameter was among the ones that yielded the best results.
For the optimal value of the co-articulation parameter t c =3 set in this article, the system has a time delay of approximately 100 ms. These computational times are suitable for a real-time operation of the system.
