The Vera am Mittag German audio-visual emotional speech database

By Michael Grimm, Kristian Kroschel, Shrikanth S. Narayanan. IEEE International Conference on Multimedia and Expo, 2008

441 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/ed2e47a250c7a868e7f46c8f45e8d78d984a1816

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

MSP-IMPROV: An Acted Corpus of Dyadic Interactions to Study Emotion Perception (2017, background): “This section overviews techniques to record emotional databases, emphasizing the role of recordings collected by actors.”
A Multimodal Database for Affect Recognition and Implicit Tagging (2012, background): “These databases mostly include speech, visual, or audio-visual data [5], [6], [7], [8].”
Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge (2011, background): “However, the experimental results presented in (Steidl et al, 2008) on the FAU Aibo Emotion Corpus indicate that the inﬂuence is rather small, at least for the current state-of-the-art in modelling pitch features and for this type of data.”
Introducing the RECOLA multimodal corpus of remote collaborative and affective interactions (2013, methodology): “The study of the complex phenomena portrayed by humans during social interactions, requires rich sets of labelled data of repeatable experiments with situations occurring in daily-life [1].”
The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing (2016, positive): “The Vera-Am-Mittag corpus [51] consists of videos extracted from the German TV show “Vera am Mittag”.”
Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast Recordings (2019, methodology): “, fatherhood, affairs, and friendship) [15].”
Induced Disgust , Happiness and Surprise : an Addition to the MMI Facial Expression Database (2010, background): “, 2007) 3 1:35 352x288 pixels @ 25Hz Unknown Scientific Yes No Vera am Mittag db (Grimm et al., 2008) 20 12:00:00 352x288 pixels @ 25Hz 16kHz Public No No”
Comparison of Gender- and Speaker-adaptive Emotion Recognition (2014, methodology): “VAM Based on the popular German TV talk-show ”Vera am Mittag” (Vera in the afternoon), the VAM-Audio database (Grimm et al., 2008) has been created at Karlsruhe Institute of Technology.”
The INTERSPEECH 2009 emotion challenge (2009, background): “Today, there are more diverse emotions covered, more elicited or even spontaneous sets of many speakers, and larger amounts of instances (up to 10k and more) of more subjects (up to 50), that are annotated by more labellers (4 (AVIC) - 17 (VAM, [6])) and partly made publicly available.”
Collecting Large, Richly Annotated Facial-Expression Databases from Movies (2012, background): “C Yes 75 Yes No No UT-Dallas13 Manual Lab 18 25 C Yes 284 No No No VAM14 Manual CTR ?”
Emotional Voice Conversion: Theory, Databases and ESD (2021, background): “JL-Corpus (James et al., 2018) is a collection of 4 New-Zealand English speakers uttering 15 sentences in 5 primary emotions with 2 repetitions, and another 10 sentences in 5 secondary emotions.”
The INTERSPEECH 2010 paralinguistic challenge (2010, neutral): “[3]), whereby CC is the primary measure.”
Learning Speaker-Specific Characteristics With a Deep Neural Architecture (2011, neutral): “, valance, activation and dominance [77].”
Deep neural networks for acoustic emotion recognition: Raising the benchmarks (2011, positive): “Finally, the Vera-Am-Mittag (VAM) corpus [4] consists of recordings taken from a German TV talk show.”
IEMOCAP: interactive emotional dyadic motion capture database (2008, background): “Some of these examples are the Belfast natural database (Douglas-Cowie et al. 2003, 2005), the VAM database (Grimm et al. 2007, 2008) and the EmoTV1 database (Abrilian et al. 2005).”
Analysis of Emotionally Salient Aspects of Fundamental Frequency for Emotion Detection (2009, background): “, the Vera am Mittag German audiovisual emotional speech database [41]).”
Automatic speech emotion recognition using modulation spectral features (2011, methodology): “…from " very good " speakers who are characterized by a high level of activity and a wide variety of emotions , while VAM II consists of utterances from " good " speakers that, though possessing high activity as well, produce a smaller scope of emotions (e.g. anger only) (Grimm et al., 2008).”
Emotion representation, analysis and synthesis in continuous space: A survey (2011, methodology): “also use the Vera am Mittag database [48] and examine the importance of different groups of speech acoustic features in the estimation”