期刊
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
卷 14, 期 2, 页码 1376-1390出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TAFFC.2021.3127390
关键词
Task analysis; Emotion recognition; Speech recognition; Affective computing; Face recognition; Measurement; Reliability; Speech emotion recognition; ordinal affective computing; representation learning of emotion similarity; triplet loss function; speech emotion retrieval
This study proposes a new formula for measuring emotional similarity between speech recordings. Instead of predicting emotional attributes or recognizing emotional categories, this formulation explores the ordinal nature of emotions by comparing emotional similarities. The study addresses questions about which emotional descriptors provide the most suitable space to assess emotional similarities and whether deep neural networks can learn representations to quantify emotional similarities robustly. By creating alternative emotional spaces using attribute-based descriptors and categorical emotions, the study shows that a meaningful embedding can be learned to assess emotional similarities, outperforming human evaluators in the same task.
This study proposes the novel formulation of measuring emotional similarity between speech recordings. This formulation explores the ordinal nature of emotions by comparing emotional similarities instead of predicting an emotional attribute, or recognizing an emotional category. The proposed task determines which of two alternative samples has the most similar emotional content to the emotion of a given anchor. This task raises some interesting questions. Which is the emotional descriptor that provide the most suitable space to assess emotional similarities? Can deep neural networks (DNNs) learn representations to robustly quantify emotional similarities? We address these questions by exploring alternative emotional spaces created with attribute-based descriptors and categorical emotions. We create the representation using a DNN trained with the triplet loss function, which relies on triplets formed with an anchor, a positive example, and a negative example. We select a positive sample that has similar emotion content to the anchor, and a negative sample that has dissimilar emotion to the anchor. The task of our DNN is to identify the positive sample. The experimental evaluations demonstrate that we can learn a meaningful embedding to assess emotional similarities, achieving higher performance than human evaluators asked to complete the same task.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据