Is Everything Fine, Grandma? Acoustic and Linguistic Modeling for Robust Elderly Speech Emotion Recognition
| Autor: | Sogancioglu, G., Verkholyak, Oxana, Kaya, H., Fedotov, Dmitrii, Cadee, Tobias, Salah, A.A., Karpov, Alexey, Sub Social and Affective Computing, Social and Affective Computing |
|---|---|
| Přispěvatelé: | Sub Social and Affective Computing, Social and Affective Computing |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
computational paralinguistics Computer Science - Machine Learning Computer Science - Computation and Language Computer science Generalization Computer Science - Human-Computer Interaction Linguistics Human-Computer Interaction (cs.HC) Machine Learning (cs.LG) Mental healthcare Linguistic analysis machine learning speech emotion recognition human-computer interaction Test set sentiment analysis Decision fusion Labeled data Emotion recognition Valence (psychology) natural language processing Computation and Language (cs.CL) speech processing |
| Zdroj: | INTERSPEECH INTERSPEECH 2020, 2097 STARTPAGE=2097;TITLE=INTERSPEECH 2020 |
| Popis: | Acoustic and linguistic analysis for elderly emotion recognition is an under-studied and challenging research direction, but essential for the creation of digital assistants for the elderly, as well as unobtrusive telemonitoring of elderly in their residences for mental healthcare purposes. This paper presents our contribution to the INTERSPEECH 2020 Computational Paralinguistics Challenge (ComParE) - Elderly Emotion Sub-Challenge, which is comprised of two ternary classification tasks for arousal and valence recognition. We propose a bi-modal framework, where these tasks are modeled using state-of-the-art acoustic and linguistic features, respectively. In this study, we demonstrate that exploiting task-specific dictionaries and resources can boost the performance of linguistic models, when the amount of labeled data is small. Observing a high mismatch between development and test set performances of various models, we also propose alternative training and decision fusion strategies to better estimate and improve the generalization performance. 5 pages, 1 figure, Interspeech 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|