Bimodal Speech Emotion Recognition Using Pre-Trained Language Models
This work addresses the problem of enhancing human-machine interaction through more accurate emotion recognition, but it is incremental as it builds on existing pre-trained models and datasets.
The authors tackled speech emotion recognition by fine-tuning pre-trained language models for text emotion recognition, achieving 69.5% accuracy on SemEval 2017 Task 4A, a 3% absolute improvement over previous state-of-the-art, and combined this with speech data to reach 73.5% accuracy on a subset of IEMOCAP dataset.
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.