By Professor Julien Epps

Preprints

Zhang X; Ahmed B; Epps J, 2026, Why Pre-trained Models Fail: Feature Entanglement in Multi-modal Depression Detection, http://dx.doi.org/10.48550/arxiv.2503.06620

Zhang X; Li Y; Zhang H; Han S; Liu H; Zhang Q; Ahmed B; Epps J, 2026, The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models, http://dx.doi.org/10.48550/arxiv.2605.29209

Zhang X; Southwell BJ; Pan S; Niu X; Ahmed B; Epps J, 2026, Why Your Tokenizer Fails in Information Fusion: A Timing-Aware Pre-Quantization Fusion for Video-Enhanced Audio Tokenization, http://dx.doi.org/10.48550/arxiv.2604.12145

Zhang X; Fang F; Gao P; Qin B; Ahmed B; Epps J, 2025, Distinctive Feature Codec: An Adaptive Efficient Speech Representation for Depression Detection, http://dx.doi.org/10.48550/arxiv.2505.18516

Zhang X; Liu D; Xiao T; Xiao C; Szalay T; Shahin M; Ahmed B; Epps J, 2025, Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction, http://dx.doi.org/10.48550/arxiv.2409.07969

Zhang X; Liu H; Zhang Q; Ahmed B; Epps J, 2025, SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information, http://dx.doi.org/10.48550/arxiv.2502.10950

Zhang X; Zhang Q; Liu H; Xiao T; Qian X; Ahmed B; Ambikairajah E; Li H; Epps J, 2025, Mamba in Speech: Towards an Alternative to Self-Attention, http://dx.doi.org/10.48550/arxiv.2405.12609

Zhang X; Liu H; Xu K; Zhang Q; Liu D; Ahmed B; Epps J, 2024, When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection, http://dx.doi.org/10.48550/arxiv.2402.13276

Zhang X; Ma J; Shahin M; Ahmed B; Epps J, 2024, Rethinking Mamba in Speech Processing by Self-Supervised Models, http://dx.doi.org/10.48550/arxiv.2409.07273

Shahin M; Epps J; Ahmed B, 2023, Phonological Level wav2vec2-based Mispronunciation Detection and Diagnosis Method, http://dx.doi.org/10.48550/arxiv.2311.07037

Shahin M; Ahmed B; Epps J, 2022, Speaker- and Age-Invariant Training for Child Acoustic Modeling Using Adversarial Multi-Task Learning, http://dx.doi.org/10.48550/arxiv.2210.10231

Dzurak AS; Epps J; Laucht A; Malaney R; Morello A; Nurdin HI; Pla JJ; Saraiva A; Yang CH, 2021, Development of an Undergraduate Quantum Engineering Degree, http://dx.doi.org/10.48550/arxiv.2110.12598

Dang T; Sethu V; Ambikairajah E; Epps J; Li H, 2021, Joint Spatio-Temporal Discretisation of Nonlinear Active Cochlear Models, http://dx.doi.org/10.48550/arxiv.2108.05993

Latif S; Rana R; Khalifa S; Jurdak R; Epps J, 2020, Direct Modelling of Speech Emotion from Raw Speech, http://dx.doi.org/10.48550/arxiv.1904.03833

Latif S; Rana R; Younis S; Qadir J; Epps J, 2020, Transfer Learning for Improving Speech Emotion Classification Accuracy, http://dx.doi.org/10.48550/arxiv.1801.06353

Latif S; Rana R; Qadir J; Epps J, 2020, Variational Autoencoders for Learning Latent Representations of Speech Emotion: A Preliminary Study, http://dx.doi.org/10.48550/arxiv.1712.08708

Latif S; Rana R; Khalifa S; Jurdak R; Epps J; Schuller BW, 2020, Multi-Task Semi-Supervised Adversarial Autoencoding for Speech Emotion Recognition, http://dx.doi.org/10.48550/arxiv.1907.06078

Sethu V; Provost EM; Epps J; Busso C; Cummins N; Narayanan S, 2019, The Ambiguous World of Emotion Representation, http://dx.doi.org/10.48550/arxiv.1909.00360

Back to profile page