A database of German emotional speech

By Felix Burkhardt, A. Paeschke, M. Rolfes, W. Sendlmeier, Benjamin Weiss. 2005

2,393 citations recorded by the source corpus.

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

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

The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems (2018, background): “The Berlin Emotional Speech Dataset [3] contains the recording of 10 different utterances by 10 different actors in 7 different emotions (neutral, anger, fear, joy, sadness, disgust and boredom) in German, making it a total of 800 utterances (counting some second version of some of the sentences).”
Learning Salient Features for Speech Emotion Recognition Using Convolutional Neural Networks (2014, background): “The second is Berlin Emotional Database (Emo-DB) [3], which also includes seven emotions (i.”
Clustering-Based Speech Emotion Recognition by Incorporating Learned Features and Deep BiLSTM (2020, methodology): “In this paper, we utilize the three public speech emotions datasets, the IEMOCAP [49] interactive emotional dyadic motion capture dataset, Emo-DB [50] berlin emotional dataset, and RAVDESS [51] Ryerson audio-visual dataset of emotional speech and songs.”
Introducing AmuS: The Amused Speech Database (2017, background): “Such data can be found in [4] (again for happy and not precisely amused smiled speech), but the amount for a single speaker might not be suﬃcient for current systems data requirements.”
MEAD: A Large-Scale Audio-Visual Dataset for Emotional Talking-Face Generation (2020, background): “There are some high-quality in-the-lab audio-visual datasets [1, 3, 9], but none of these take emotion information into consideration in design.”
A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, background): “of Emotional Speech (Emo-DB) [68] contains about 500 utterances spoken by 10 actors (5 men and 5 women) in a happy, angry, anxious, fearful, bored and disgusting way.”
The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing (2016, neutral): “It was introduced by [48].”
Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast Recordings (2019, methodology): “IEMOCAP [10] 12 h26 m 10 acted English MSP-IMPROV [19] 9 h35 m 12 acted English CREMA-D [2] 7,442 samples 91 acted English Chen Bimodal [20] 9,900 samples 100 acted English Emo-DB [6] 22 m 10 acted German GEMEP [21] 1,260 samples 10 acted - VAM-Audio [15] 48 m 47 spont.”
An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era (2022, methodology): “Prior to the introduction of ESD, researchers used either small-scale datasets created explicitly for ESS [110], [113], [120] or relied on the standard SER datasets, such as IEMOCAP [176] and EMO-DB [177].”
A comprehensive survey on feature selection in the various fields of machine learning (2021, methodology): “IEMOCAP [163], EMO-DB [164], SAVEE [165], CASIA [166], eNTERFACE’05 [167], EMOVO [168], MASC [169] Speech Emotion Recognition Table 18 The description of various types of features used in the FS task for speech processing applications”
SPEECH EMOTION RECOGNITION USING SUPPORT VECTOR MACHINE (2010, methodology): “A Berlin Emotional database [5] is used for feature extraction and training SVM.”
Emotional Voice Conversion: Theory, Databases and ESD (2021, methodology): “The Berlin Emotional Speech Dataset (EmoDB) (Burkhardt et al., 2005) collects 10 sentences read by 10 speakers with 7 emotions.”
Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition (2013, background): “…available and highly popular databases, namely the TUM Audio-Visual Interest Corpus (TUM AVIC) [16], Berlin Emotional Speech Database (EMO-DB) [17], eNTERFACE [18], Speech Under Simulated and Actual Stress (SUSAS) [19], and the “Vera am Mittag” (VAM) database [17], [20] are chosen as source…”
OpenEAR — Introducing the munich open-source emotion and affect recognition toolkit (2009, methodology): “Finally, four ready-to-use model-sets are provided for recognition of six basic emotion categories (trained on the Berlin Speech Emotion Database (EMO-DB) [2] and the eNTERFACE database), for recognition of emotion in a continuous three-dimensional feature space spanned by activation, valence, and d”
Paralinguistics in speech and language - State-of-the-art and the challenge (2013, methodology): “Probably the most frequently used (acted) data set is the Berlin Emotional Speech database (Burkhardt et al., 2005a)—for results on this set cf., e.g., Schuller et al. (2010c), Gaurav (2008).”
Deep neural networks for acoustic emotion recognition: Raising the benchmarks (2011, background): “As an example, in Figure 2, 2D GerDA features of speaker 4 of the EMOD binary arousal task (top) and of speaker group 2 of the binary valence AVIC task as well as the resulting classification boundaries are plotted.”