Xilin Jiang

Publication Activity (10 Years)

Years Active: 2013-2024
Publications (10 Years): 15

Top Topics

Source Separation

Prosodic Features

Top Venues

IEEE Signal Process. Lett.

Publications

Xilin Jiang, Cong Han, Nima Mesgarani
Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation. CoRR (2024)
Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani
Exploring Self-supervised Contrastive Learning of Spatial Sound Event Representation. ICASSP (2024)
Siavash Shams, Sukru Samet Dindar, Xilin Jiang, Nima Mesgarani
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model. CoRR (2024)
Xilin Jiang, Yinghao Aaron Li, Adrian Nicolas Florea, Cong Han, Nima Mesgarani
Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis. CoRR (2024)
Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani
Listen, Chat, and Edit: Text-Guided Soundscape Modification for Enhanced Auditory Experience. CoRR (2024)
Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani
Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation. CoRR (2023)
Xilin Jiang, Yinghao Aaron Li, Nima Mesgarani
DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes. CoRR (2023)
Yinghao Aaron Li, Cong Han, Xilin Jiang, Nima Mesgarani
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions. CoRR (2023)
Yinghao Aaron Li, Cong Han, Xilin Jiang, Nima Mesgarani
HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform. CoRR (2023)
Yinghao Aaron Li, Cong Han, Xilin Jiang, Nima Mesgarani
Phoneme-Level Bert for Enhanced Prosody of Text-To-Speech with Grapheme Predictions. ICASSP (2023)
Xilin Jiang, Yinghao Aaron Li, Nima Mesgarani
DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes. INTERSPEECH (2023)
Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis
Learning Representations for New Sound Classes With Continual Self-Supervised Learning. IEEE Signal Process. Lett. 29 (2022)
Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis
Compute and Memory Efficient Universal Sound Source Separation. J. Signal Process. Syst. 94 (2) (2022)
Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis
Learning Representations for New Sound Classes With Continual Self-Supervised Learning. CoRR (2022)
Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis
Compute and memory efficient universal sound source separation. CoRR (2021)
René-Jean Essiambre, M. A. Mestre, Roland Ryf, Alan H. Gnauck, Robert W. Tkach, Andrew R. Chraplyvy, Yi Sun, Xilin Jiang, Robert Lingle
Demonstration of broadband inter-modal four-wave mixing in graded-index few-mode fibers. OFC/NFOEC (2013)