Disentanglement for audio-visual emotion recognition using multitask setup

Autor:	Peri, Raghuveer, Parthasarathy, Srinivas, Bradshaw, Charles, Sundaram, Shiva
Rok vydání:	2021
Předmět:	Electrical Engineering and Systems Science - Image and Video Processing Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with multitask learning have shown additional performance improvements. However, such multitask models entangle information between the tasks, encoding the mutual dependencies present in label distributions in the real world data used for training. This work explores the disentanglement of multimodal signal representations for the primary task of emotion recognition and a secondary person identification task. In particular, we developed a multitask framework to extract low-dimensional embeddings that aim to capture emotion specific information, while containing minimal information related to person identity. We evaluate three different techniques for disentanglement and report results of up to 13% disentanglement while maintaining emotion recognition performance. Comment: Accepted for ICASSP 2021, 5 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2102.06269 Zobrazit plný text záznamu View this record from Arxiv