Emotional speech: Towards a new generation of databases

By Ellen Douglas-Cowie, Nick Campbell, R. Cowie, Peter J. Roach. Speech Communication, 2003

513 citations recorded by the source corpus.

Subfields: Experimental and Cognitive Psychology, Social Psychology

View Paper: https://www.semanticscholar.org/paper/b39fd7d058ce5cdeae26008a281e766b2ad7051e

How researchers see this paper

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

In Experimental and Cognitive Psychology

In Social Psychology

Citations in the corpus

The HUMAINE Database: Addressing the Collection and Annotation of Naturalistic and Induced Emotional Data (2007, unknown): “Belfast Naturalistic Database [10] Nature of material: The database consists of audiovisual sedentary interactions from TV chat shows and religious programs, and discussions between old acquaintances.”
Databases, features and classifiers for speech emotion recognition: a review (2018, background): “Speech from interviews with specialists such as psychologists and scientist specialized in phonetics (Douglas-Cowie et al. 2003).”
Describing the emotional states that are expressed in speech (2003, methodology): “For example, the database collected by the Reading group (Douglas-Cowie et al., 2003) describes an utterance as moving from ‘‘hate’’ to ‘‘vengeful anger’’.”
Emotional speech recognition: Resources, features, and methods (2006, methodology): “An alternative is speech from interviews with specialists, such as psychologists and scientists specialized in phonetics (Douglas-Cowie et al., 2003).”
Emotion Recognition through Multiple Modalities: Face, Body Gesture, Speech (2008, background): “More recently, some attempts to collect multimodal data were made: some examples of multimodal databases can be found in [9] [10] [11].”
Automatic Analysis of Facial Affect: A Survey of Registration, Representation, and Recognition (2015, unknown): “Belfast Naturalistic [36] Yes 4+N 12 A/V 125 298 @ - - -”
Automatic speech emotion recognition using modulation spectral features (2011, background): “In the past, classification tasks have drawn dominant attention of the research community (Cowie et al., 2001; Douglas-Cowie et al., 2003; Ververidis and Kotropoulos, 2006; Shami and Verhelst, 2007).”
Speech Recognition Using Deep Neural Networks: A Systematic Review (2019, background): “The applications of emotion recognition clearly appear in [24]–[26] perceiving the speaker emotional status in telephone call center conversations and supplying feedback to an operator for observing purposes, categorizing voice mail messages based on emotions articulated by callers, and recognizing ”
Emotion recognition from speech: a review (2012, background): “Most of the existing emotional speech databases used for developing emotion systems are too small in size (Douglas-Cowie et al. 2003).”
MSP-IMPROV: An Acted Corpus of Dyadic Interactions to Study Emotion Perception (2017, background): “Index Terms—Emotion elicitation, audiovisual emotional dataset, emotional evaluation, emotion recognition Ç”
Analysis of Emotionally Salient Aspects of Fundamental Frequency for Emotion Detection (2009, background): “Therefore, it is not surprising that the models built with these individual databases (usually offline) do not easily generalize to different databases or online recognition tasks in which blending of emotions is observed [26].”
Introducing the RECOLA multimodal corpus of remote collaborative and affective interactions (2013, background): “It conforms with many desirable criteria suggested by emotion researchers [13] and thus may serve as a valuable common resource for future studies on automated analysis of socio-emotional behaviors, as well as for those related to emotion contagion and interpersonal synchrony [14].”
IEMOCAP: interactive emotional dyadic motion capture database (2008, background): “analyzed some of the existing emotional databases [28], and”
CREMA-D: Crowd-sourced Emotional Multimodal Actors Dataset (2014, background): “…are available that contain rated visual displays [16], [17], [18], [19], auditory stimuli [20], [21], [22], [23], [24] and audio-visual clips [25], [26], [27], [28], [29], but these are relatively small, with perceptual rating only from a few raters or do not contain independent ratings for…”