Welcome to the LiLAB 

Mission Statement

Our work is dedicated to creating cutting-edge algorithms for digital signal processing, specifically designed for speech, audio, and multimodal signals. We focus on impactful applications across various domains, including user-device interfaces, medical technology, media and entertainment, mobility solutions, and educational tools. Our objective is to craft highly efficient solutions by integrating advanced statistical methods, filter implementation, machine learning, and deep learning approaches, all while navigating real-world limitations. Our techniques span a wide range, from feature engineering to state-of-the-art machine learning strategies.

1. Our paper "Reliability-Aware Speech-Text Fusion for Multilingual Mixed Emotion Recognition with Label Distribution Learning" was accepted by ICSPS 2026 and will be presented soon in Xiamen, China.

2. Our co-authored paper "Leveraging Modality-Specific Label Distributions for Enhanced Multimodal Emotion Recognition" will be presented soon at INTERSPEECH 2026, in Sydney, Australia.

3. Accepted Journal Publications 2026

[1] X. Shi, X. Li and T. Toda, "Emotion Similarity and Shift: Modeling Temporal Dynamic Interactions for Emotion Prediction in Conversation," in IEEE Transactions on Audio, Speech and Language Processing, doi: 10.1109/TASLPRO.2026.3684422.

[2] X. Li, N. Luo, F. Yu, X. Shi, J. Li and Y. Liu, "Multi-Task Deep Learning With Over-Sampling and Style Randomization for Improved Cross-Regional Bird Vocalization Recognition," in IEEE Transactions on Audio, Speech and Language Processing, vol. 34, pp. 1709-1724, 2026, doi: 10.1109/TASLPRO.2026.3675794.

[3] Shi X, He J, Li X, Toda T. A Comprehensive Study on the Effectiveness of ASR Representations for Noise-Robust Speech Emotion Recognition. IEEE Transactions on Audio, Speech and Language Processing.  vol. 34, pp. 707-722, 2026, doi: 10.1109/TASLPRO.2026.3654273. 

[4] Shenzhi Li, Xingfeng Li, Hao Zhu, Chao Li, Peng Wang, PFDBooster: A Unified Post-Image Fusion Dual-Domain Boosting Paradigm, Knowledge-Based Systems, 2026, 115577, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2026.115577.

4. Three papers were accepted by BigData 2025 (acceptance rate 18.7%) @Macau Dec. 2025

5. Four co-authored papers were accepted by Interspeech 2025 @Netherlands Aug. 2025

6. Accepted Journal Publications 2025

[1] K. Li, K. Zaman, X. Li, M. Akagi, J. Dang and M. Unoki, "Machine Anomalous Sound Detection Using Spectral-Temporal Modulation Representations Derived From Machine-Specific Filterbanks," in IEEE Transactions on Audio, Speech and Language Processing, vol. 33, pp. 2059-2073, 2025, doi: 10.1109/TASLPRO.2025.3570956.

[2] Y. Liu, X. Chen, Z. Peng, Y. Li, X. Li, P. Song, M. Unoki, and Z. Zhao, "Enhancing Speech Emotion Recognition With Conditional Emotion Feature Diffusion and Progressive Interleaved Learning Strategy," in IEEE Transactions on Audio, Speech and Language Processing, vol. 33, pp. 1787-1800, 2025, doi: 10.1109/TASLPRO.2025.3561606.

[3] J. He, X. Shi, C. H. Hu, J. Mi, X. Li and T. Toda, "M4SER: Multimodal, Multirepresentation, Multitask, and Multistrategy Learning for Speech Emotion Recognition," in IEEE Transactions on Audio, Speech and Language Processing, vol. 33, pp. 4055-4070, 2025, doi: 10.1109/TASLPRO.2025.3614428. 

[4] Yang Liu, Xin Chen, Yarong Li, Jie Ma, Xiaoqi Yang, Yuan Song, Xiaolei Meng, Yongwei Li, Xingfeng Li, Zhen Zhao, "Enhanced Speech Emotion Recognition in Noisy Environments: Adaptive Emotion Denoising Diffusion Approach With Iterative Confidence Learning Strategy," in IEEE Internet of Things Journal, vol. 12, no. 20, pp. 43241-43254, 15 Oct.15, 2025, doi: 10.1109/JIOT.2025.3595096. 

[5] Xingfeng Li, Ningfeng Luo, Feifei Yu, Junjie Li, Kai Li, Yongwei Li, Zhen Zhao, Yang Liu, Xiaohan Shi, "Human Auditory Representation Learning for cross-dialect bird species recognition" in Ecological Informatics,  Volume 93, February 2026, 103554. https://doi.org/10.1016/j.ecoinf.2025.103554