Speech Emotion Recognition with Dual-Sequence LSTM Architecture
Abstract
Speech Emotion Recognition (SER) has emerged as a critical component of the next generation human-machine interfacing technologies. In this work, we propose a new dual-level model that predicts emotions based on both MFCC features and mel-spectrograms produced from raw audio signals. Each utterance is preprocessed into MFCC features and two mel-spectrograms at different time-frequency resolutions. A standard LSTM processes the MFCC features, while a novel LSTM architecture, denoted as Dual-Sequence LSTM (DS-LSTM), processes the two mel-spectrograms simultaneously. The outputs are later averaged to produce a final classification of the utterance. Our proposed model achieves, on average, a weighted accuracy of 72.7% and an unweighted accuracy of 73.3%---a 6% improvement over current state-of-the-art unimodal models---and is comparable with multimodal models that leverage textual information as well as audio signals.
Keywords
Cite
@article{arxiv.1910.08874,
title = {Speech Emotion Recognition with Dual-Sequence LSTM Architecture},
author = {Jianyou Wang and Michael Xue and Ryan Culhane and Enmao Diao and Jie Ding and Vahid Tarokh},
journal= {arXiv preprint arXiv:1910.08874},
year = {2020}
}
Comments
Accepted by ICASSP 2020