Designing and Evaluating Speech Emotion Recognition Systems: A reality check case study with IEMOCAP

Abstract

There is an imminent need for guidelines and standard test sets to allow direct and fair comparisons of speech emotion recognition (SER). While resources, such as the Interactive Emotional Dyadic Motion Capture (IEMOCAP) database, have emerged as widely-adopted reference corpora for researchers to develop and test models for SER, published work reveals a wide range of assumptions and variety in its use that challenge reproducibility and generalization. Based on a critical review of the latest advances in SER using IEMOCAP as the use case, our work aims at two contributions: First, using an analysis of the recent literature, including assumptions made and metrics used therein, we provide a set of SER evaluation guidelines. Second, using recent publications with open-sourced implementations, we focus on reproducibility assessment in SER.

arXiv commentAccepted at ICASSP 2023

References in corpus (6)

• Emotion Recognition From Speech With Recurrent Neural Networks
• Towards Learning a Universal Non-Semantic Representation of Speech
• Efficient Speech Emotion Recognition Using Multi-Scale CNN and Attention
• A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding
• TRILLsson: Distilled Universal Paralinguistic Speech Representations
• Universal Paralinguistic Speech Representations Using Self-Supervised Conformers

Cited by in corpus (1)

• A Multi-Task, Multi-Modal Approach for Predicting Categorical and Dimensional Emotions