OpenEAR — Introducing the munich open-source emotion and affect recognition toolkit

By Florian Eyben, Martin Wöllmer, Björn Schuller. 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, 2009

453 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ee236171abf2341ece4fc559f849201790b2c095

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 Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

Paralinguistics in speech and language - State-of-the-art and the challenge (2013, methodology): “In this Challenge, an extended set of features compared to the INTERSPEECH 2009 Emotion Challenge (Schuller et al., 2009b) was given to the participants, again choosing the open-source toolkit openSMILE (Eyben et al., 2009).”
COVAREP — A collaborative voice analysis repository for speech technologies (2014, unknown): “Existing toolboxes partly address this issue [1, 2, 3, 4, 5].”
Speech emotion recognition using deep neural network and extreme learning machine (2014, methodology): “The SVM is the most commonly used classiﬁer for global features[11, 12].”
AVEC 2012: the continuous audio/visual emotion challenge (2012, methodology): “is given to the participants, again using the freely available open-source Emotion and Affect Recognition (openEAR) [5] toolkit’s feature extraction backend openSMILE [6].”
Recurrent Neural Networks for Emotion Recognition in Video (2015, methodology): “It uses 1582 features extracted with the open-source Emotion and Affect Recognition (openEAR) [12] toolkit which uses openSMILE [11] as backend.”
AVEC 2011-The First International Audio/Visual Emotion Challenge (2011, methodology): “In this Challenge, an extended set of features with respect to the INTERSPEECH 2009 Emotion Challenge (384 features) [13] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [14] is given to the participants, again using the freely available open-source Emotion and Affect Recognition (ope”
Introducing shared-hidden-layer autoencoders for transfer learning and their application in acoustic emotion recognition (2014, methodology): “To ensure reproducibility as well, the open source toolkit openEAR toolkit [27] was used with the pre-defined EC configuration.”
A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, background): “OpenSMILE [167] is a popular audio feature extraction toolkit that extracts all key features of the speech.”
Opensmile: the munich versatile and fast open-source audio feature extractor (2010, methodology): “The openEAR project [5] builds on openSMILE features for doing emotion recognition.”
Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition (2013, methodology): “To ensure reproducibility as well, the open source toolkit openEAR toolkit [21] was used to extract the feature set with the pre-deﬁned openEAR conﬁguration for the 2009 challenge.”
A survey of multimodal sentiment analysis (2017, methodology): “Pitch and speech pause were extracted using openEAR [130].”
Online Driver Distraction Detection Using Long Short-Term Memory (2011, methodology): “Applying our openEAR toolkit [29], we computed a set of 55 statistical functionals for each of the 18 low-level signals as a basis for the framewise classification task.”
The INTERSPEECH 2010 paralinguistic challenge (2010, methodology): “In this Challenge an extended set of features compared to the INTERSPEECH 2009 Emotion Challenge [4] is given to the participants, again choosing the open-source Emotion and Affect Recognition toolkit’s feature extracting backend openSMILE [5].”
Learning Salient Features for Speech Emotion Recognition Using Convolutional Neural Networks (2014, methodology): “Table II compares the accuracy and the standard deviation for RAW, TEO, A1 [23], A2 [8], LIF, SDFA(no_or), SDFA(no_s),”
AVEC 2014: 3D Dimensional Affect and Depression Recognition Challenge (2014, methodology): “extended set of features with respect to the INTERSPEECH 2009 Emotion Challenge (384 features) [24] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [25] is given to the participants, again using the freely available open-source Emotion and Affect Recognition (openEAR) [8] toolkit’s fe”
Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge (2011, methodology): “The Munich open-source Emotion and Aﬀect Recognition Toolkit (openEAR) (Eyben et al., 2009) is the ﬁrst of its kind to provide a free open source toolkit that integrates all three necessary components: feature extraction (by the fast openSMILE 7 back-end (Eyben et al., 2010c)), classiﬁers, and…”
Deep neural networks for acoustic emotion recognition: Raising the benchmarks (2011, methodology): “For each considered emotion recognition task, acoustic feature vectors of 6 552 dimensions were extracted using the openEAR toolkit [3] as 39 functionals of 56 acoustic Low-Level Descriptors (LLDs) including first and second order delta regression coefficients.”