GMP-TL: Gender-augmented Multi-scale Pseudo-label Enhanced Transfer Learning for Speech Emotion Recognition
Abstract
The continuous evolution of pre-trained speech models has greatly advanced Speech Emotion Recognition (SER). However, current research typically relies on utterance-level emotion labels, inadequately capturing the complexity of emotions within a single utterance. In this paper, we introduce GMP-TL, a novel SER framework that employs gender-augmented multi-scale pseudo-label (GMP) based transfer learning to mitigate this gap. Specifically, GMP-TL initially uses the pre-trained HuBERT, implementing multi-task learning and multi-scale k-means clustering to acquire frame-level GMPs. Subsequently, to fully leverage frame-level GMPs and utterance-level emotion labels, a two-stage model fine-tuning approach is presented to further optimize GMP-TL. Experiments on IEMOCAP show that our GMP-TL attains a WAR of 80.0% and an UAR of 82.0%, achieving superior performance compared to state-of-the-art unimodal SER methods while also yielding comparable results to multimodal SER approaches.
Cite
@article{arxiv.2405.02151,
title = {GMP-TL: Gender-augmented Multi-scale Pseudo-label Enhanced Transfer Learning for Speech Emotion Recognition},
author = {Yu Pan and Yuguang Yang and Heng Lu and Lei Ma and Jianjun Zhao},
journal= {arXiv preprint arXiv:2405.02151},
year = {2024}
}
Comments
Accepted to SLT2024