By Mr Xiangyu Zhang

Preprints

Zhang X; Fang F; Gao P; Qin B; Ahmed B; Epps J, 2025, Distinctive Feature Codec: Adaptive Segmentation for Efficient Speech Representation, http://arxiv.org/abs/2505.18516v1

Zhang X; Ahmed B; Epps J, 2025, Why Pre-trained Models Fail: Feature Entanglement in Multi-modal Depression Detection, http://arxiv.org/abs/2503.06620v1

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://arxiv.org/abs/2502.10950v2

Zhang X; Liu D; Xiao T; Xiao C; Szalay T; Shahin M; Ahmed B; Epps J, 2024, Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction, http://arxiv.org/abs/2409.07969v2

Zhang X; Ma J; Shahin M; Ahmed B; Epps J, 2024, Rethinking Mamba in Speech Processing by Self-Supervised Models, http://arxiv.org/abs/2409.07273v1

Zhang X; Zhang Q; Liu H; Xiao T; Qian X; Ahmed B; Ambikairajah E; Li H; Epps J, 2024, Mamba in Speech: Towards an Alternative to Self-Attention, http://arxiv.org/abs/2405.12609v6

Joshi A; Renzella J; Bhattacharyya P; Jha S; Zhang X, 2024, Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy, http://arxiv.org/abs/2405.09854v2

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://arxiv.org/abs/2402.13276v2

Zhang X; Liu D; Liu H; Zhang Q; Meng H; Garcia LP; Chng ES; Yao L, 2024, Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model, http://arxiv.org/abs/2402.10642v2

Li SS; Zhang X; Zhou S; Shu H; Liang R; Liu H; Garcia LP, 2022, PQLM -- Multilingual Decentralized Portable Quantum Language Model for Privacy Protection, http://arxiv.org/abs/2210.03221v5

Zhang X; Li SS; He Z; Togneri R; Garcia LP, 2022, End-to-End Lyrics Recognition with Self-supervised Learning, http://arxiv.org/abs/2209.12702v4

Back to profile page