Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition
This provides an efficient solution for emotion and sentiment analysis tasks, though it appears incremental as it builds on existing Transformer methods with modulation.
The paper tackles emotion recognition by proposing two lightweight Transformer-based architectures with modulation that combine linguistic and acoustic inputs, achieving state-of-the-art or competitive results on datasets like IEMOCAP, MOSI, MOSEI, and MELD.
This paper aims to bring a new lightweight yet powerful solution for the task of Emotion Recognition and Sentiment Analysis. Our motivation is to propose two architectures based on Transformers and modulation that combine the linguistic and acoustic inputs from a wide range of datasets to challenge, and sometimes surpass, the state-of-the-art in the field. To demonstrate the efficiency of our models, we carefully evaluate their performances on the IEMOCAP, MOSI, MOSEI and MELD dataset. The experiments can be directly replicated and the code is fully open for future researches.