Deep learning for robust feature generation in audiovisual emotion recognition

By Yelin Kim, Honglak Lee, Emily Mower Provost. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013

409 citations recorded by the source corpus.

Subfields: Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/b3aec2122d5043d920f81b2c52efe735a05388bb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

Deep Multimodal Representation Learning: A Survey (2019, background): “Based on multimodal deep belief networks, several applications such as audio-visual emotion recognition [25], audio-visual speech recognition [27], and information trustworthiness estimation [100] have been reported.”
Feature learning based on SAE-PCA network for human gesture recognition in RGBD images (2015, background): “For example, Kim et al. [29] used deep belief network to generate audio-visual features for emotion classi ﬁ cation in an unsupervised context.”
End-to-End Multimodal Emotion Recognition Using Deep Neural Networks (2017, background): “[23] proposed four different DBN architectures with one of them being a basic”
Learning in high-dimensional multimedia data: the state of the art (2015, background): “The focus of feature selection is to select a subset of variables from the input which can efficiently describe the input data while reducing effects from noise or irrelevant variables and still provide good prediction results [26, 42, 78].”
Multimodal Machine Learning: A Survey and Taxonomy (2017, methodology): “Joint Neural networks Images + Audio [145], [151], [227] Images + Text [184] Graphical models Images + Text [198] Images + Audio [104] Sequential Audio + Video [96], [152] Images + Text [166]”
Speech emotion recognition using convolutional and Recurrent Neural Networks (2016, neutral): “In addition, audio/video based multimodal emotion recognition approaches were experimented in [15-16].”
Hierarchical Convolutional Neural Networks for EEG-Based Emotion Recognition (2017, methodology): “proposed an automatic emotion recognition system on the basis of DBN in an audiovisual task and offered the performance comparison with SVM [35].”
Uncertainty Estimation in Bayesian Neural Networks And Links to Interpretability (2018, background): “In recent years, deep neural networks (DNNs) have emerged as top-performing models [41] that serve as flexible function approximators [45] or automatic feature generators [50, 37].”
High-level feature representation using recurrent neural network for speech emotion recognition (2015, methodology): “Recently, deep learning techniques have been applied in this field to obtain high-level representation for speech and emotion recognition [4, 6, 7, 8].”
Improved Multimodal Deep Learning with Variation of Information (2014, background): “There have been several applications of multimodal learning from multiple domains such as emotion [13] and speech [10] recognition with audio-visual data, robotics applications with visual and depth data [15, 17, 32, 23], or medical applications with visual and temporal data [26].”
Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning (2020, background): “Multimodal representation learning frameworks can be divided into three types: (a) joint representation which aims to learn a shared semantic subspace [63,71,26,3,48,51,95]; (b) an encoder-decoder framework which aims to translate from one modality into another and keep their semantics consistent [3”
DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices (2016, background): “The range of inference tasks impacted by deep learning includes the recognition of: faces [2], emotions [3], objects [4] and words [5].”