@inproceedings{2b44ce73f62b4df39d01fb8b30ff03ed,
title = "Multi-Microphone Speech Emotion Recognition Using the Hierarchical Token-Semantic Audio Transformer Architecture",
abstract = "The performance of most emotion recognition systems degrades in real-life situations ({\textquotedblleft}in the wild{\textquotedblright} scenarios) where the audio is contaminated by reverberation. Our study explores new methods to alleviate the performance degradation of Speech Emotion Recognition (SER) algorithms and develop a more robust system for adverse conditions. We propose processing multi-microphone signals to address these challenges and improve emotion classification accuracy. We adopt a state-of-the-art transformer model, the Hierarchical Token-semantic Audio Transformer (HTS-AT), to handle multi-channel audio inputs. We evaluate two strategies: averaging mel-spectrograms across channels and summing patch-embedded representations. Our multi-microphone model achieves superior performance compared to single-channel baselines when tested on real-world reverberant environments.",
keywords = "human-robot interaction, speech emotion recognition",
author = "Ohad Cohen and Gershon Hazan and Sharon Gannot",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 ; Conference date: 06-04-2025 Through 11-04-2025",
year = "2025",
doi = "10.1109/icassp49660.2025.10887873",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Rao, \{Bhaskar D\} and Isabel Trancoso and Gaurav Sharma and Mehta, \{Neelesh B.\}",
booktitle = "2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 - Proceedings",
address = "United States",
}