Realistic Speech-Driven Talking Video Generation with Personalized Pose

Table 2

Mean Opinion Score (MOS) of 100 participants on 4 questions. Q1: completenessof body. Q2: the face is clear. Q3: the body movement is correlated with audio. Q4: overall quality.

	Q1	Q2	Q3	Q4
Synth.	4.14	4.37	2.92	3.75
TTS	4.10	3.80	2.58	3.39
Real	4.31	4.42	4.33	4.40