IEMOCAP: interactive emotional dyadic motion capture database

By Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Ebrahim (Abe) Kazemzadeh, Emily Mower Provost, Samuel Kim, Jeannette N. Chang, Sungbok Lee, Shrikanth S. Narayanan. 2008

4,482 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Social Psychology, Sentiment & Opinion Analysis, Speech & Audio

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 Social Psychology

In Sentiment & Opinion Analysis

In Speech & Audio

Citations in the corpus

The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems (2018, background): “IEMOCAP contains audio-visual recordings of 5 sessions of dyadic conversations between a male and a female subjects.”
SUPERB: Speech processing Universal PERformance Benchmark (2021, methodology): “The most widely used ER dataset IEMOCAP [31] is adopted, and we follow the conventional evaluation protocol: we drop the unbalance emotion classes to leave the ﬁnal four classes (neutral, happy, sad, angry) with a similar amount of data points and cross-validates on ﬁve folds of the standard splits.”
Factorized Multimodal Transformer for Multimodal Sequential Learning (2019, methodology): “FMT is compared to previously proposed approaches for multimodal sequential learning over multimodal sentiment analysis (CMU-MOSI) (Zadeh et al., 2016), multimodal emotion recognition (IEMOCAP) (Busso et al., 2008), and multimodal personality traits recognition (POM) (Park et al., 2014).”
Memory Fusion Network for Multi-view Sequential Learning (2018, neutral): “We perform experiments on IEMOCAP dataset (Busso et al. 2008).”
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, methodology): “An abridged dialogue from the IEMOCAP dataset Busso et al.[14].”
Emotion-Aware Prosodic Phrasing for Expressive Text-to-Speech (2023, methodology): “The objective experimental results on IEMOCAP dataset suggest that our EmoPP outperforms all baselines in terms of break prediction accuracy.”
Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis (2019, methodology): “This section presents and discusses results on the CMU-MOSI, CMU-MOSEI, and IEMOCAP datasets.”
DialogueRNN: An Attentive RNN for Emotion Detection in Conversations (2018, methodology): “IEMOCAP: IEMOCAP (Busso et al. 2008) dataset contains videos of two-way conversations of ten unique speakers, where only the first eight speakers from session one to four belong to the train-set.”
Expressive TTS Training With Frame and Style Reconstruction Loss (2020, methodology): “We train a SER as the style descriptor on IEMOCAP dataset [89], which consists of five sessions.”
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT (2023, methodology): “For the SER task, we collect corpora including MELD (Poria et al., 2018), IEMOCAP (Busso et al., 2008), RAVDESS (Livingstone & Russo, 2018), TESS (Pichora-Fuller & Dupuis, 2020), Crema-D (Cao et al., 2014), Emov-DB (Adigwe et al., 2018), and SAVEE (Jackson & Haq, 2014).”
A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, methodology): “Chen et al. [199] proposed the attention-based 3D-RNNs to learn discriminative features for SER. Experimental results show that the Attention-3D-RNNs can exceed the performance of SOTA SER on IEMOCAP and Emo-DB in terms of unweighted average recall.”
Introducing AmuS: The Amused Speech Database (2017, background): “Several databases containing emotional speech exist, such as [4,5].”
Databases, features and classifiers for speech emotion recognition: a review (2018, methodology): “The interactive emotional dyadic motion capture database (IEMOCAP) (Busso et al. 2008), which was collected by the Speech Analysis and Interpretation Laboratory (SAIL) at the University of Southern California (USC).”