publications

Papers and preprints, newest first.

Also listed on Google Scholar.

2026

  1. ICASSP
    SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models
    Qiaolin Wang, Xilin Jiang, Linyang He, Junkai Wu, and Nima Mesgarani
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026
    arXiv HTML
  2. COLM
    AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs’ Contextual and Cultural Knowledge and Thinking
    Xilin Jiang*, Qiaolin Wang*, Junkai Wu*, Xiaomin He*, Zhongweiyang Xu*, and 28 more authors
    In Conference on Language Modeling (COLM), 2026
    arXiv Website
  3. Preprint
    Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO
    Xilin Jiang, Riki Shimizu, Sukru Samet Dindar, Junkai Wu, Zhongweiyang Xu, and 1 more author
    arXiv:2607.27756, 2026
    arXiv

2025

  1. WASPAABest Paper Award
    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
    Xilin Jiang*, Junkai Wu*, Vishal Choudhari, and Nima Mesgarani
    In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2025
    PDF

2024

  1. SLT
    Just ASR + LLM? A Study on Speech Large Language Models’ Ability to Identify and Understand Speaker in Spoken Dialogue
    Junkai Wu*, Xulin Fan*, Bo-Ru Lu, Xilin Jiang, Nima Mesgarani, and 2 more authors
    In IEEE Spoken Language Technology Workshop (SLT), 2024
    PDF
  2. ICASSP
    Meta-AF Echo Cancellation for Improved Keyword Spotting
    Jonah Casebeer, Junkai Wu, and Paris Smaragdis
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
    PDF

2023

  1. ACL Findings
    Listen, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language Recognition
    Liming Wang, Junrui Ni, Heting Gao, Jialu Li, Kai Chieh Chang, and 4 more authors
    In Findings of the Association for Computational Linguistics: ACL 2023, Jul 2023
    PDF
  2. WASPAA
    Unsupervised Improvement of Audio-Text Cross-Modal Representations
    Zhepei Wang, Cem Subakan, Krishna Subramani, Junkai Wu, Tiago Tavares, and 2 more authors
    In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Jul 2023
    PDF Code

2022

  1. IEEE SPL
    Learning Representations for New Sound Classes With Continual Self-Supervised Learning
    Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, and 2 more authors
    IEEE Signal Processing Letters, Jul 2022
    PDF Code
  2. IWAENC
    Meta-Learning for Adaptive Filters with higher-order Frequency Dependencies
    Junkai Wu, Jonah Casebeer, Nicholas J. Bryan, and Paris Smaragdis
    In International Workshop on Acoustic Signal Enhancement (IWAENC), Jul 2022
    PDF Code