Finnish speech emotion analysis combines text and audio features for improved valence prediction

Researchers have investigated the impact of linguistic and acoustic features on the perception of emotion in spontaneous Finnish speech. Their study, utilizing a newly released affective speech corpus, found that combining text- and audio-based features significantly improved the regression results for valence prediction compared to using either modality alone. However, for arousal prediction, the complementary effect of combining these features was not substantial, aligning with prior findings from studies in other languages. AI

IMPACT Provides insights into multimodal emotion recognition, potentially improving AI systems that process spoken language.

RANK_REASON Academic paper on speech analysis and emotion. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Finnish
• Gotit.pub
• Hugging Face
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →