Beyond Isolated Utterances: Conversational Emotion Recognition

TL;DR

This paper advances conversational emotion recognition by proposing transformer-based models, introducing a novel augmentation scheme, and leveraging interlocutor-aware embeddings to improve emotion detection in conversations.

Contribution

It introduces a transformer-based approach for CER, proposes DiverseCatAugment for data augmentation, and develops an interlocutor-aware transformer model for better context understanding.

Findings

Transformer models outperform ResNet-34 and BiLSTM in CER.

DiverseCatAugment improves micro-f1 by 3.3% on conversations.

Interlocutor-aware transformer further enhances performance.

Abstract

Speech emotion recognition is the task of recognizing the speaker's emotional state given a recording of their utterance. While most of the current approaches focus on inferring emotion from isolated utterances, we argue that this is not sufficient to achieve conversational emotion recognition (CER) which deals with recognizing emotions in conversations. In this work, we propose several approaches for CER by treating it as a sequence labeling task. We investigated transformer architecture for CER and, compared it with ResNet-34 and BiLSTM architectures in both contextual and context-less scenarios using IEMOCAP corpus. Based on the inner workings of the self-attention mechanism, we proposed DiverseCatAugment (DCA), an augmentation scheme, which improved the transformer model performance by an absolute 3.3% micro-f1 on conversations and 3.6% on isolated utterances. We further enhanced the performance by introducing an interlocutor-aware transformer model where we learn a dictionary of interlocutor index embeddings to exploit diarized conversations.