Xilin Jiang

38 papers A* 3A 1Misc 4Journal 24Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking.
CoRR
Xilin Jiang, Qiaolin Wang, Junkai Wu, Xiaomin He, Zhongweiyang Xu, Yinghao Ma, Minshuo Piao, Kaiyi Yang, Xiuwen Zheng, Riki Shimizu, Yicong Chen, Arsalan Firoozi, Gavin Mischler, Sukru Samet Dindar, Richard J. Antonello, Linyang He, Tsun-An Hsieh, Xulin Fan, Yulun Wu, Yuesheng Ma, Chaitanya Amballa, Weixiong Chen, Jiarui Hai, Ruisi Li, Vishal Choudhari, Cong Han, Yinghao Aaron Li, Adeen Flinker, Mounya Elhilali, Emmanouil Benetos, Mark Hasegawa-Johnson, Romit Roy Choudhury, Nima Mesgarani
2026 A* conf
DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis.
AAAI
Yinghao Aaron Li, Xilin Jiang, Fei Tao, Cheng Niu, Kaifeng Xu, Juntong Song, Nima Mesgarani
2025 — conf
AAD-LLM: Neural Attention-Driven Auditory Scene Understanding.
ACL (1)
Xilin Jiang, Sukru Samet Dindar, Vishal Choudhari, Stephan Bickel, Ashesh D. Mehta, Guy M. McKhann II, Daniel Friedman, Adeen Flinker, Nima Mesgarani
2025 J jnl
AAD-LLM: Neural Attention-Driven Auditory Scene Understanding.
CoRR
Xilin Jiang, Sukru Samet Dindar, Vishal Choudhari, Stephan Bickel, Ashesh D. Mehta, Guy M. McKhann II, Adeen Flinker, Daniel Friedman, Nima Mesgarani
2025 A* conf
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior.
ICML
Zhongweiyang Xu, Xulin Fan, Zhong-Qiu Wang, Xilin Jiang, Romit Roy Choudhury
2025 J jnl
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior.
CoRR
Zhongweiyang Xu, Xulin Fan, Zhong-Qiu Wang, Xilin Jiang, Romit Roy Choudhury
2025 — conf
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation.
WASPAA
Xilin Jiang, Junkai Wu, Vishal Choudhari, Nima Mesgarani
2025 J jnl
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation.
CoRR
Xilin Jiang, Junkai Wu, Vishal Choudhari, Nima Mesgarani
2025 Misc conf
Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation.
ICASSP
Xilin Jiang, Cong Han, Nima Mesgarani
2025 J jnl
Exploring Finetuned Audio-LLM on Heart Murmur Features.
CoRR
Adrian Nicolas Florea, Xilin Jiang, Nima Mesgarani, Xiaofan Jiang
2025 A* conf
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations.
EMNLP
Linyang He, Qiaolin Wang, Xilin Jiang, Nima Mesgarani
2025 J jnl
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations.
CoRR
Linyang He, Qiaolin Wang, Xilin Jiang, Nima Mesgarani
2025 J jnl
Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience.
IEEE J. Sel. Top. Signal Process.
Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani
2025 J jnl
Sci-Phi: A Large Language Model Spatial Audio Descriptor.
CoRR
Xilin Jiang, Hannes Gamper, Sebastian Braun
2025 J jnl
SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models.
CoRR
Qiaolin Wang, Xilin Jiang, Linyang He, Junkai Wu, Nima Mesgarani
2025 Misc conf
Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis.
ICASSP
Xilin Jiang, Yinghao Aaron Li, Adrian Nicolas Florea, Cong Han, Nima Mesgarani
2025 — conf
StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion.
NAACL (Long Papers)
Yinghao Aaron Li, Xilin Jiang, Cong Han, Nima Mesgarani
2024 J jnl
Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation.
CoRR
Xilin Jiang, Cong Han, Nima Mesgarani
2024 Misc conf
Exploring Self-supervised Contrastive Learning of Spatial Sound Event Representation.
ICASSP
Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani
2024 — conf
Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify And Understand Speaker in Spoken Dialogue.
SLT
Junkai Wu, Xulin Fan, Bo-Ru Lu, Xilin Jiang, Nima Mesgarani, Mark Hasegawa-Johnson, Mari Ostendorf
2024 J jnl
Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue.
CoRR
Junkai Wu, Xulin Fan, Bo-Ru Lu, Xilin Jiang, Nima Mesgarani, Mark Hasegawa-Johnson, Mari Ostendorf
2024 J jnl
Listen, Chat, and Edit: Text-Guided Soundscape Modification for Enhanced Auditory Experience.
CoRR
Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani
2024 — conf
SSAMBA: Self-Supervised Audio Representation Learning With Mamba State Space Model.
SLT
Siavash Shams, Sukru Samet Dindar, Xilin Jiang, Nima Mesgarani
2024 J jnl
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model.
CoRR
Siavash Shams, Sukru Samet Dindar, Xilin Jiang, Nima Mesgarani
2024 J jnl
Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis.
CoRR
Xilin Jiang, Yinghao Aaron Li, Adrian Nicolas Florea, Cong Han, Nima Mesgarani
2024 J jnl
Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation.
CoRR
Yinghao Aaron Li, Xilin Jiang, Jordan Darefsky, Ge Zhu, Nima Mesgarani
2024 J jnl
StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion.
CoRR
Yinghao Aaron Li, Xilin Jiang, Cong Han, Nima Mesgarani
2023 A conf
DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes.
INTERSPEECH
Xilin Jiang, Yinghao Aaron Li, Nima Mesgarani
2023 J jnl
DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes.
CoRR
Xilin Jiang, Yinghao Aaron Li, Nima Mesgarani
2023 J jnl
Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation.
CoRR
Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani
2023 J jnl
HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform.
CoRR
Yinghao Aaron Li, Cong Han, Xilin Jiang, Nima Mesgarani
2023 J jnl
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions.
CoRR
Yinghao Aaron Li, Cong Han, Xilin Jiang, Nima Mesgarani
2023 Misc conf
Phoneme-Level Bert for Enhanced Prosody of Text-To-Speech with Grapheme Predictions.
ICASSP
Yinghao Aaron Li, Cong Han, Xilin Jiang, Nima Mesgarani
2022 J jnl
Compute and Memory Efficient Universal Sound Source Separation.
J. Signal Process. Syst.
Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis
2022 J jnl
Learning Representations for New Sound Classes With Continual Self-Supervised Learning.
CoRR
Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis
2022 J jnl
Learning Representations for New Sound Classes With Continual Self-Supervised Learning.
IEEE Signal Process. Lett.
Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis
2021 J jnl
Compute and memory efficient universal sound source separation.
CoRR
Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis
2013 — conf
Demonstration of broadband inter-modal four-wave mixing in graded-index few-mode fibers.
OFC/NFOEC
René-Jean Essiambre, M. A. Mestre, Roland Ryf, Alan H. Gnauck, Robert W. Tkach, Andrew R. Chraplyvy, Yi Sun, Xilin Jiang, Robert Lingle