no code implementations • 17 Dec 2023 • Vikramjit Mitra, Jingping Nie, Erdrin Azemi
Representations derived from models such as BERT (Bidirectional Encoder Representations from Transformers) and HuBERT (Hidden units BERT), have helped to achieve state-of-the-art performance in dimensional speech emotion recognition.
1 code implementation • 12 Sep 2023 • Ran Liu, Ellen L. Zippi, Hadi Pouransari, Chris Sandino, Jingping Nie, Hanlin Goh, Erdrin Azemi, Ali Moin
To achieve effective pretraining in the presence of potential distributional shifts, we propose a frequency-aware masked autoencoder ($\texttt{bio}$FAME) that learns to parameterize the representation of biosignals in the frequency space.
no code implementations • 3 Mar 2023 • Vikramjit Mitra, Vasudha Kowtha, Hsiang-Yun Sherry Chien, Erdrin Azemi, Carlos Avendano
We investigated the use of pre-trained model representations for estimating dimensional emotions, such as activation, valence, and dominance, from speech.
no code implementations • 2 Jul 2022 • Vikramjit Mitra, Hsiang-Yun Sherry Chien, Vasudha Kowtha, Joseph Yitan Cheng, Erdrin Azemi
We investigate the use of pre-trained model representations to improve valence estimation from acoustic speech signal.
1 code implementation • 30 Jun 2020 • Joseph Y. Cheng, Hanlin Goh, Kaan Dogrusoz, Oncel Tuzel, Erdrin Azemi
Datasets for biosignals, such as electroencephalogram (EEG) and electrocardiogram (ECG), often have noisy labels and have limited number of subjects (<100).