Following the published press release of September 24th, 2021 (corrected version of October 5th), the summary of the analysis results is now to be presented. The german politicians Annalena Baerbock, Armin Laschet and Olaf Scholz had been analyzed by audEERING’s Audio AI while their chancellor candidation. audEERING’s analyzes do not refer to the content of the speeches, but to acoustic, linguistic and emotional characteristics. These are identified by using scientific procedures and audEERING’s award-winning AI technologies such as devAIce ™ and openSMILE ™.
Acoustic Analysis: openSMILE ™
A part of the features analyzed for the acoustic analysis were pauses, rhythm and articulation. Speaking is not only unconsciously shaped on the basis of these characteristics, but can also be consciously designed. The way of speaking is an important part of delivering information and leading an audience through it in the context of a speech.
Pauses and Speaking Time
Armin Laschet’s speeches shows the highest number of pauses. A large number of pauses can appear charismatic and dominant and have a positive effect on intelligibility. In comparison to the other candidates, he’s additionally building short phrases between the pauses, what helps the audience to follow.
Syllables, Speaking Speed and Rhythm Characteristics
With regard to the rhythm parameter, the analysis shows results for syllables per second. A high rate of speech – in combination with other parameters such as articulation – is associated with charisma and dominance. With five syllables per second, Olaf Scholz speaks a little faster than the other candidates. However, the speed deviation is lowest in Olaf Scholz’s speeches and highest in Baerbock’s. This dynamic characteristic helps to captivate the audience and lead them through the information. After all, Olaf Scholz also varies his speaking rhythm less than Baerbock and Laschet. Monotonous speaking can be tiring for the audience.
In comparison to the other candidates, Annalena Baerbock speaks with the highest articulation precision – Olaf Scholz with the lowest. A low articulation precision is in its mode of action a balancing act between calmness and fatigue. Precise articulation is linked to an energetic body tension, which in turn has a positive effect on how the person will be perceived.
Emotion Analysis: Arousal and Dominance via devAIce ™
In the area of emotion analysis, the acoustic expression of emotional activation and dominance is examined. Here Baerbock is most active in her emotional expression and that’s how she can signal involvement. Her speeches are also the most dominant. This makes her appear most committed and empathetic compared to the other candidates.
“The current analysis shows a remarkable ambiguity of a candidate compared to the analyzes carried out so far.” explains CEO Dagmar Schuller. Before audEERING has provided clear positive results within different elections from for the subsequently chosen person in advance.
If you are interested in more information about audEERING and Audio AI, make sure to follow us on Social Media and take a deeper look on our website: audeering.com