Confidence Measures in Speech Emotion Recognition Based on Semi-supervised Learning
Confidence Measures in Speech Emotion Recognition Based on Semi-supervised Learning
复制标题
基于半监督学习的语音情感识别置信度测量
DOI：
10.21437/interspeech.2012-127
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Björn Schuller
中科院分区：
文献类型：
--
作者：
Jun Deng;Björn Schuller
尽管语音情感识别（SER）系统所做预测的准确性正在提高，但人们对预测的可信度知之甚少。为了阐明这一点，我们提出了一种基于半监督学习的SER系统置信度度量。在半监督学习过程中，实现了五个常用的数据库和手动创建的置信度标签来训练分类器。当SER系统预测未知测试话语的标签时，这些分类器作为话语的可靠性估计器，并输出一系列置信度，这些置信度被组合成单个置信度度量。我们的实验结果令人印象深刻地表明，所提出的信心度量在表明我们对预测情绪的信任程度方面是有效的。
Even though the accuracy of predictions made by speech emotion recognition (SER) systems is increasing in precision, little is known about the confidence of the predictions. To shed some light on this, we propose a confidence measure for SER systems based on semi-supervised learning. During the semi-supervised learning procedure, five frequently used databases with manually created confidence labels are implemented to train classifiers. When the SER system predicts the label for an unknown test utterance, these classifiers serve as a reliability estimator for the utterance and output a series of confidence ratios that are combined into a single confidence measure. Our experimental results impressively show that the proposed confidence measure is effective in indicating how much we can trust the predicted emotion.