The INTERSPEECH 2009 emotion challenge

By Björn Schuller, Stefan Steidl, Anton Batliner. Interspeech, 2009

1,032 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/c4abae7850c84264eff9573e05354a84e10adbf6

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

AVEC 2013: the continuous audio/visual emotion and depression recognition challenge (2013, methodology): “2011, an extended set of features with respect to the INTERSPEECH 2009 Emotion Challenge (384 features) [22] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [23] is given to the participants, again using the freely available open-source Emotion and Affect Recognition (openEAR) [7] too”
A Survey on perceived speaker traits: Personality, likability, pathology, and the first challenge (2015, background): “In 2009 to 2012, challenges (Schuller et al., 2009, 2010, 2011b, 2012, 2013a,b) were organised at the INTERSPEECH conferences that featured several different aspects of paralinguistics: topics of interest were not what the speaker said, i. e., word recognition, or the semantics behind word…”
Emotion recognition using a hierarchical binary decision tree approach (2011, methodology): “82% relative) over the best baseline results presented in the Emotion Challenge baseline summarized in (Schuller et al., 2009).”
The INTERSPEECH 2010 paralinguistic challenge (2010, methodology): “This INTERSPEECH 2010 Paralinguistic Challenge represents an extension of last year’s Challenge [4] by broadening the scope, including several different tasks such as age, gender, and level of interest.”
Controlling Emotion Strength with Relative Attribute for End-to-End Speech Synthesis (2019, neutral): “) In total, 384 dimensional audio features are extracted, as suggested in [28].”
Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings (2018, background): “These vector representations have been shown useful for many applications, such as speaker identiﬁcation [13] and audio emotion classiﬁcation [14], in addition to spoken term detection (STD) [15, 16, 17], because such vector representations can be applied to standard classiﬁers to determine the…”
Paralinguistics in speech and language - State-of-the-art and the challenge (2013, methodology): “Examples for some recent approaches that eal with vocal outbursts include sighs and yawns (Russell et al., 2003), laughs (Campbell et al., 2005; Batliner et al., n press), cries (Pal et al., 2006), hesitations and consent (Schuller et al., 2009a), and coughs (Matos et al., 2006).”
Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition (2013, methodology): “To keep in line with the INTERSPEECH 2009 EC [15], we decided to use its standardised feature set of 12 functionals applied to 2 × 16 acoustic Low-Level Descriptors (LLDs) including their ﬁrst order delta regression coefﬁcients as shown in Table III.”
AVEC 2012: the continuous audio/visual emotion challenge (2012, background): “2009 Emotion Challenge (384 features) [14] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [15]”
OpenEAR — Introducing the munich open-source emotion and affect recognition toolkit (2009, methodology): “Moreover, features for the Interspeech 2009 Emotion Challenge [10] were extracted with openEAR.”
Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011 (2012, methodology): “This method was successfully ported to recognize sentiments or emotion in Schuller et al. (2005a, 2009a).”
Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection (2016, background): “Many common tasks can be formulated as sequence classification including speaker recognition [10], audio emotion classification [11], spoken term detection (STD) [12–14], dialogue act detection [15–17], key term extraction [18–21], etc.”
Review on Psychological Stress Detection Using Biosignals (2019, background): “In the area of speech emotion recognition, some first attempts of establishing and using a general protocol test procedure were introduced [266].”
MSP-IMPROV: An Acted Corpus of Dyadic Interactions to Study Emotion Perception (2017, methodology): “We consider the set provided for the 2009 Interspeech Emotion Challenge [66].”
Introducing shared-hidden-layer autoencoders for transfer learning and their application in acoustic emotion recognition (2014, methodology): “To keep in line with the INTERSPEECH 2009 EC [24], we decided to use its standard feature set of 12 functionals applied to 2 × 16 acoustic Low-Level Descriptors (LLDs) including their first order delta regression coefficients as shown in Table 4.”
Emotion recognition from spontaneous speech using Hidden Markov models with deep belief networks (2013, methodology): “The best baseline system in [5] achieved a 38.”
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”