Deep neural networks for acoustic emotion recognition: Raising the benchmarks

By A. Stuhlsatz, Christine Meyer, Florian Eyben, Thomas Zielke, H. Meier, Björn Schuller. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2011

294 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/09777b14e073db61ac6e5ecae45a6c25b1c22cbd

How researchers see this paper

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

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Improving speech emotion recognition via Transformer-based Predictive Coding through transfer learning (2018, background): “Speech emotion recognition, as an important aspect of emotion recognition, has shown tremendous progress under the development of deep learning [1-10].”
Deep learning of feature representation with multiple instance learning for medical image analysis (2014, methodology): “Deep learning as classifiers are used in acoustic emotion recognition [21] and object classes in ImageNet [22].”
Emotion recognition from spontaneous speech using Hidden Markov models with deep belief networks (2013, methodology): “[19] used generatively pre-trained ANNs to learn discriminative features of low dimension and found improvement in both weighted and unweighted recall on multiple emotion corpora.”
Paralinguistics in speech and language - State-of-the-art and the challenge (2013, background): “Then, multi-corpus and cross-corpus evaluations such as the ones described above for age and gender (cf. Section 6.1) and as recently done for emotion (Stuhlsatz et al., 2011; Schuller et al., 2010c; Eyben et al., 2010a) could be part of future research on combined speaker trait analysis.”
Learning Salient Features for Speech Emotion Recognition Using Convolutional Neural Networks (2014, background): “For SER, Stuhlsatz et al. [36] used generatively pre-trained artificial neural networks (ANNs) to learn discriminative features of low dimension and found improvement in both weighted and unweighted recall on multiple emotion corpora.”
Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011 (2012, methodology): “Indicatively, in Yang et al. (2009a) it is demonstrated that the features selected to build a classifier are not that robust for speech emotion recognition in a different language.”
Hybrid Deep Neural Network--Hidden Markov Model (DNN-HMM) Based Speech Emotion Recognition (2013, methodology): “In [8], a Generalized Discriminant Analysis (GerDA) based on DNNs, is proposed to learn the discriminative features for classifying high or low of arousal and positive or negative valence.”
Speech Emotion Recognition Using Deep Learning Techniques: A Review (2019, methodology): “A comparison of DNN with GMM for SER has been presented in [124], where both the techniques are tested for the”
Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition (2013, unknown): “In [11], a generalised discriminant analysis based on deep neural networks was proposed to learn discriminative features of low dimension for optimisation from a large set of acoustic features for emotion recognition which slightly rises the benchmark.”
Social signal classification using deep blstm recurrent neural networks (2014, unknown): “Motivated by the impressive success of deep neural networks (DNNs) in the fields of ASR and paralinguistics [12, 13] we recently applied a deep neural network (DNN) model on the task of vocalization detection and localization [14].”
Speech emotion recognition (2018, unknown): “,(42) a long-short term memory recurrent neural network (LSTM RNN) is used, and in Stuhlsatz et al.(35) a restricted Boltzman machinesbased feed-forward deep net learns features), several authors followed this idea to learn the feature representation with a deep neural network, for example, Cibau(7)”
Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching (2018, methodology): “For instance, in [12], [13] a DNN is used”
Evaluating deep learning architectures for Speech Emotion Recognition (2017, background): “The first experiment was conducted to investigate the number of context frames required for SER.”
Deep learning for robust feature generation in audiovisual emotion recognition (2013, methodology): “[16] took a different approach for learning acoustic features in speech emotion recognition using Generalized Discriminant Analysis (GerDA) based on Deep Neural Networks (DNNs).”
Automatic speech emotion recognition using recurrent neural networks with local attention (2017, methodology): “The authors in [6] used a Deep Neural Network (DNN) on top of traditional utterance-level statistical features to improve the recognition accuracy compared to conventional classifiers such as Support Vector Machines (SVM).”