Bimodal Speech Emotion Recognition Using Pre-Trained Language Models
Abstract
Speech emotion recognition is a challenging task and an important step towards more natural human-machine interaction. We show that pre-trained language models can be fine-tuned for text emotion recognition, achieving an accuracy of 69.5% on Task 4A of SemEval 2017, improving upon the previous state of the art by over 3% absolute. We combine these language models with speech emotion recognition, achieving results of 73.5% accuracy when using provided transcriptions and speech data on a subset of four classes of the IEMOCAP dataset. The use of noise-induced transcriptions and speech data results in an accuracy of 71.4%. For our experiments, we created IEmoNet, a modular and adaptable bimodal framework for speech emotion recognition based on pre-trained language models. Lastly, we discuss the idea of using an emotional classifier as a reward for reinforcement learning as a step towards more successful and convenient human-machine interaction.
Keywords
Cite
@article{arxiv.1912.02610,
title = {Bimodal Speech Emotion Recognition Using Pre-Trained Language Models},
author = {Verena Heusser and Niklas Freymuth and Stefan Constantin and Alex Waibel},
journal= {arXiv preprint arXiv:1912.02610},
year = {2019}
}
Comments
Life-Long Learning for Spoken Language Systems ASRU 2019