# Speech Emotion Recognition with Dual-Sequence LSTM Architecture Source: [Speech Emotion Recognition with Dual-Sequence LSTM Architecture]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:28:00.017Z Authors: Jianyou Wang, Michael Xue, Ryan Culhane, Enmao Diao, Jie Ding, Vahid Tarokh Published: 2019-10-20T02:04:55.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Speech Emotion Recognition on IEMOCAP Speaker-dependent random train-test split](): Speech Emotion Recognition; IEMOCAP Speaker-dependent random train-test split; WA: 72.7. ## Original sources and implementation [Original paper]() [PDF]()