Looking for Affect in Spontaneous Finnish Speech through Linguistic Interpretability
2026-07-27 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how both the sound and the words of Finnish speech affect how people perceive emotions like happiness or sadness (valence) and energy level (arousal). They used a new collection of natural Finnish speech to see if combining audio features (like tone) and text features (like word choice) predicts emotions better than using either alone. They found that combining both helps predict valence but does not improve arousal much. Their results agree with earlier studies on other languages and provide new insights for Finnish speech.
affective speech corpusvalencearousalacoustic featurestext-based featuresspeech emotion recognitionFinnish languageregression modelingperceptual process
Authors
Kalle Lahtinen, Liisa Mustanoja, Okko Räsänen
Abstract
Existing research on affect in speech has shown how acoustic surface characteristics and content-related linguistic aspects of speech both relate to perceived emotional arousal and valence. However, it is not clear what the relative contributions of these two factors are in the perceptual process. This is especially true for Finnish, for which most existing studies focus on either acoustic-phonetic or text analysis. This paper presents a study where we systematically explore the combinatory role of text- and audio-based features in modeling the human perception of valence and arousal using a newly released affective speech corpus for spontaneous Finnish. We show that the combination of text- and audio-based features improves valence regression results over the individual modalities, whereas for arousal regression the complementary effect is not substantial. The results support prior findings from other languages, providing new data and knowledge on spontaneous Finnish speech.