@InProceedings{Khatri2025_1231,
<br/>   author = {Phrashant Khatri and Hansjörg Mixdorff and Preeti Rao and Albert Rilliard},
<br/>   booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2025},
<br/>   title = {Recognition of audio-visual attitudes},
<br/>   year = {2025},
<br/>   editor = {Sven Grawunder},
<br/>   month = mar,
<br/>   pages = {19--26},
<br/>   publisher = {TUDpress, Dresden},
<br/>   abstract  = {We investigate audiovisual features for classifying attitudes, a key aspect 
of communication that has been less studied than emotion recognition. Using a German 
audiovisual dataset labeled with speaker intention and perceived attitude, we test 
acoustic and visual features that have achieved state-of-the-art emotion recognition 
results. Our classification achieves performance significantly above chance for 16 
attitudes, closely aligning with perceptual ratings in diversity across attitudes and 
speakers. We emphasize the challenges of processing nuanced expressions compared to 
prototypical emotions. While audiovisual classifications outperform humans in some 
areas, they fall short of fully leveraging the combined strengths of audio and visual 
cues. This study highlights the potential for improved cross-modal fusion and calls for 
further research on visual feature extraction in affective studies.},
<br/>   isbn = {978-3-95908-803-9},
<br/>   issn = {0940-6832},
<br/>   keywords = {Multimodal Perception of Speech and Non-verbal Cues},
<br/>   url = {https://www.essv.de/pdf/2025_19_26.pdf},
<br/>}