LanSER: Language-Model Supported Speech Emotion Recognition
Abstract
Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of unlabeled data by inferring weak emotion labels via pre-trained large language models through weakly-supervised learning. For inferring weak labels constrained to a taxonomy, we use a textual entailment approach that selects an emotion label with the highest entailment score for a speech transcript extracted via automatic speech recognition. Our experimental results show that models pre-trained on large datasets with this weak supervision outperform other baseline models on standard SER datasets when fine-tuned, and show improved label efficiency. Despite being pre-trained on labels derived only from text, we show that the resulting representations appear to model the prosodic content of speech.
Cite
@article{arxiv.2309.03978,
title = {LanSER: Language-Model Supported Speech Emotion Recognition},
author = {Taesik Gong and Josh Belanich and Krishna Somandepalli and Arsha Nagrani and Brian Eoff and Brendan Jou},
journal= {arXiv preprint arXiv:2309.03978},
year = {2023}
}
Comments
Presented at INTERSPEECH 2023