Speech Emotion Recognition using Self-Supervised Features
This work addresses emotion recognition from speech, which is important for applications like human-computer interaction, but it is incremental as it builds on existing self-supervised methods.
The paper tackled speech emotion recognition by investigating self-supervised features in a modular system, achieving state-of-the-art results on the IEMOCAP dataset and showing that speech-only features can match multimodal systems.
Self-supervised pre-trained features have consistently delivered state-of-art results in the field of natural language processing (NLP); however, their merits in the field of speech emotion recognition (SER) still need further investigation. In this paper we introduce a modular End-to- End (E2E) SER system based on an Upstream + Downstream architecture paradigm, which allows easy use/integration of a large variety of self-supervised features. Several SER experiments for predicting categorical emotion classes from the IEMOCAP dataset are performed. These experiments investigate interactions among fine-tuning of self-supervised feature models, aggregation of frame-level features into utterance-level features and back-end classification networks. The proposed monomodal speechonly based system not only achieves SOTA results, but also brings light to the possibility of powerful and well finetuned self-supervised acoustic features that reach results similar to the results achieved by SOTA multimodal systems using both Speech and Text modalities.